Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to food fortification policies and deficiencies in specific nutrients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by present tense verbs

    np_acts-logits-general · gemini-2.0-flash

    states, countries, and current facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     becomes
    -0.93
     become
    -0.90
     Become
    -0.83
    becomes
    -0.80
    AddTagHelper
    -0.79
     becoming
    -0.77
     Becomes
    -0.76
    become
    -0.76
     BECOME
    -0.73
    becoming
    -0.71
    POSITIVE LOGITS
     regularly
    1.00
     routinely
    0.95
     operates
    0.80
     operate
    0.77
     Regularly
    0.77
     frequently
    0.71
     regularmente
    0.71
     periodically
    0.68
     annually
    0.68
    frequently
    0.66
    Act Density 0.538%

    No Known Activations