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

    Neuronpedia

    INDEX
    Explanations

    commands and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    皚
    0.57
     औष
    0.50
    蓴
    0.50
    wahati
    0.50
    巖
    0.50
    atletas
    0.49
    𒈾
    0.49
    靄
    0.48
    swadian
    0.48
    眥
    0.48
    POSITIVE LOGITS
    :
    0.59
    s
    0.59
    _
    0.56
     A
    0.53
    p
    0.53
    c
    0.52
    '
    0.52
    t
    0.52
    d
    0.51
    ’
    0.51
    Act Density 0.051%

    No Known Activations