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

    Neuronpedia

    INDEX
    Explanations

    profile or profiles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    1.12
    ين
    1.09
    ले
    0.97
    ко
    0.96
    ك
    0.94
    лі
    0.93
    но
    0.89
    <0xB9>
    0.86
    .".
    0.86
     ۸
    0.86
    POSITIVE LOGITS
    Profile
    1.16
     profile
    1.13
    이었다
    1.10
     profiles
    1.08
    ol
    1.02
    m
    1.01
     Profile
    0.95
     profilo
    0.95
    and
    0.94
     Profiles
    0.91
    Act Density 0.007%

    No Known Activations