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

    Neuronpedia

    INDEX
    Explanations

    our

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    .RemoveAt
    -0.06
    alizace
    -0.06
    zw
    -0.06
    رات
    -0.06
    _fit
    -0.06
    Attrs
    -0.06
     Zoom
    -0.06
    %c
    -0.06
    Pad
    -0.05
    POSITIVE LOGITS
    ーブル
    0.07
     ベ
    0.07
    ]
    0.06
    스터
    0.06
    .good
    0.06
     legislation
    0.06
    .pow
    0.06
    .gr
    0.06
    -authored
    0.06
     dispenser
    0.06
    Act Density 0.013%

    No Known Activations