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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _iteration
    -0.07
    сят
    -0.06
    ラック
    -0.06
    .NewRequest
    -0.06
    کنون
    -0.06
     resultMap
    -0.06
    ыџN
    -0.06
     feminism
    -0.06
     '">
    -0.06
    _yaml
    -0.06
    POSITIVE LOGITS
    stit
    0.07
     đánh
    0.07
    �
    0.07
     who
    0.06
    who
    0.06
     Ash
    0.06
    sometimes
    0.06
     mái
    0.06
    ческой
    0.06
     forfeiture
    0.06
    Act Density 0.105%

    No Known Activations