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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    🦚
    -0.07
    _variables
    -0.07
    筵
    -0.07
     самостоя
    -0.07
    טען
    -0.07
    牠
    -0.07
     ::::::::
    -0.07
     Dez
    -0.06
    تحق
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Wa
    0.07
    (block
    0.06
     anthology
    0.06
     CEO
    0.06
    htaking
    0.06
    ulnerable
    0.06
    (Type
    0.06
     squeez
    0.06
     reasonable
    0.06
     comes
    0.06
    Act Density 0.002%

    No Known Activations