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

    Neuronpedia

    INDEX
    Explanations

    local files or program scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    axter
    0.40
     liqueur
    0.39
    𝘼
    0.39
    វិញ
    0.38
    sister
    0.38
     сестра
    0.38
     Schwester
    0.37
    INH
    0.36
    ኮ
    0.36
     sister
    0.36
    POSITIVE LOGITS
     Local
    0.62
     local
    0.59
     স্থানীয়
    0.58
    局部
    0.57
    Local
    0.56
    local
    0.54
     localize
    0.53
     LOCAL
    0.52
     localidades
    0.52
    本地
    0.52
    Act Density 0.001%

    No Known Activations