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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     connecting
    -0.06
    datagrid
    -0.06
     �
    -0.06
     coordinates
    -0.06
    ('~
    -0.06
     Choi
    -0.05
     Mutex
    -0.05
     package
    -0.05
     Yu
    -0.05
    _UID
    -0.05
    POSITIVE LOGITS
    чні
    0.07
     Shuffle
    0.07
     från
    0.07
    /t
    0.07
     Accuracy
    0.06
    Accuracy
    0.06
     esos
    0.06
     серпня
    0.06
    kHz
    0.06
    реж
    0.06
    Act Density 0.020%

    No Known Activations