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

    Neuronpedia

    INDEX
    Explanations

    Research reports and articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,String
    -0.07
    .dispose
    -0.06
    Basket
    -0.06
    ��
    -0.06
    /'+
    -0.06
     vás
    -0.06
    _PI
    -0.06
     shooting
    -0.06
    break
    -0.06
     ka
    -0.06
    POSITIVE LOGITS
     tx
    0.07
     přev
    0.06
     cer
    0.06
    철
    0.06
     jails
    0.06
     );
↵
↵
    0.06
    ulen
    0.06
    StackNavigator
    0.06
     bác
    0.06
     OTHERWISE
    0.06
    Act Density 0.024%

    No Known Activations