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

    Neuronpedia

    INDEX
    Explanations

    data formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    带动
    0.37
    趔
    0.37
    peza
    0.36
    τυχ
    0.36
    OnClick
    0.35
    ᗰ
    0.34
    醤
    0.34
    ExtensionsPath
    0.33
    град
    0.33
    潜力
    0.33
    POSITIVE LOGITS
     format
    2.00
     formats
    1.90
     formato
    1.83
    格式
    1.76
     formatos
    1.76
    format
    1.75
     Format
    1.73
     формат
    1.66
    形式
    1.63
    Format
    1.59
    Act Density 0.108%

    No Known Activations