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

    Neuronpedia

    INDEX
    Explanations

    .G

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     //{
    -0.06
    ------------
    -0.06
    _product
    -0.06
     Murder
    -0.06
     modificar
    -0.06
     KUR
    -0.06
    ंद
    -0.06
     데이터
    -0.06
    ulant
    -0.06
    device
    -0.06
    POSITIVE LOGITS
    itized
    0.08
    Bet
    0.07
    ipeg
    0.07
     sophisticated
    0.07
     köy
    0.06
     베스트
    0.06
    /target
    0.06
    gow
    0.06
    �
    0.06
     tightened
    0.06
    Act Density 0.041%

    No Known Activations