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

    Neuronpedia

    INDEX
    Explanations

    id or RoleId followed by :

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ató
    0.52
     ratified
    0.52
    нке
    0.51
     Еўро
    0.50
     době
    0.50
     Spitzen
    0.49
    вної
    0.48
    ﮗ
    0.48
    宻
    0.48
    onha
    0.47
    POSITIVE LOGITS
    m
    0.75
    Id
    0.73
    de
    0.71
    na
    0.71
    c
    0.68
    to
    0.66
    g
    0.65
    of
    0.65
    ul
    0.63
    d
    0.63
    Act Density 0.035%

    No Known Activations