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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing the concept of having or lacking something

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

    "Nothing" or "something" followed by "to"

    np_acts-logits-general · gemini-2.0-flash

    have nothing to do with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isissez
    -0.51
     cứng
    -0.49
     ***!
    -0.48
    mployed
    -0.47
    [];
    -0.47
     tây
    -0.47
    <?
    -0.46
    Demografía
    -0.46
    england
    -0.45
     attivo
    -0.45
    POSITIVE LOGITS
     everything
    0.82
    tagHelperRunner
    0.80
     EVERYTHING
    0.79
    everything
    0.75
    ValueStyle
    0.74
     anything
    0.74
     Everything
    0.73
    Everything
    0.71
    Anything
    0.71
     relation
    0.68
    Act Density 0.109%

    No Known Activations