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

    Neuronpedia

    INDEX
    Explanations

    names, words, and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    st
    -3.64
    v
    -3.61
    3
    -3.59
    u
    -3.56
    7
    -3.50
    s
    -3.41
    4
    -3.38
    by
    -3.34
    ing
    -3.31
    t
    -3.30
    POSITIVE LOGITS
    ᠌
    2.89
    erráneo
    2.66
    xnn
    2.66
    beef
    2.56
    eroon
    2.55
    玏
    2.52
    gucig
    2.48
    饧
    2.47
    翾
    2.45
    یین
    2.44
    Act Density 0.000%

    No Known Activations