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

    Neuronpedia

    INDEX
    Explanations

    person

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Що
    -0.07
    ICAST
    -0.07
    �
    -0.07
     Conspiracy
    -0.06
     incons
    -0.06
    SEMB
    -0.06
    >null
    -0.06
    .Translate
    -0.06
    --,
    -0.06
    )을
    -0.06
    POSITIVE LOGITS
    .truth
    0.07
     TT
    0.07
     नर
    0.07
     candle
    0.07
     durable
    0.06
     gymn
    0.06
     erotic
    0.06
     drawn
    0.06
     Reviewed
    0.06
    _ie
    0.06
    Act Density 0.009%

    No Known Activations