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

    Neuronpedia

    INDEX
    Explanations

    written

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     czę
    -0.07
    levard
    -0.07
     vem
    -0.06
     auss
    -0.06
     reveal
    -0.06
    (INVOKE
    -0.06
    _repository
    -0.06
    珙
    -0.06
     impe
    -0.06
    React
    -0.06
    POSITIVE LOGITS
    一�
    0.07
    .Dialog
    0.07
    长约
    0.07
    帮扶
    0.07
    もう
    0.07
     mężczy
    0.07
    .WaitFor
    0.07
     DEFAULT
    0.06
    _obj
    0.06
     opi
    0.06
    Act Density 0.002%

    No Known Activations