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

    Neuronpedia

    INDEX
    Explanations

    warning signals or indications of caution

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

    warning signs or alerts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ">$
    -0.45
     tub
    -0.43
     plu
    -0.42
    stateProvider
    -0.41
    ITURE
    -0.40
    lorette
    -0.39
    Simply
    -0.39
     Plu
    -0.38
    Cole
    -0.38
    Plu
    -0.37
    POSITIVE LOGITS
     warning
    1.23
     Warning
    1.17
     warnings
    1.15
    warning
    1.09
    Warnings
    1.04
     Warnings
    1.04
    warnings
    1.00
    Warning
    0.99
    warn
    0.99
     warn
    0.98
    Act Density 0.009%

    No Known Activations