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

    Neuronpedia

    INDEX
    Explanations

    set notation examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    2.58
    ating
    2.24
    isted
    2.21
     Resmi
    2.19
    ้
    2.19
    ค์
    2.17
    га
    2.15
     freshly
    2.12
    lijk
    2.11
    ates
    2.07
    POSITIVE LOGITS
    ت
    2.91
    inputStream
    2.82
    ባድ
    2.77
    此之外
    2.74
    le
    2.42
    ल
    2.41
    minded
    2.37
    വ
    2.34
    Owned
    2.32
    ur
    2.32
    Act Density 0.002%

    No Known Activations