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

    Neuronpedia

    INDEX
    Explanations

    shell variable expansion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ぜ
    0.39
     قرب
    0.38
    .#
    0.37
    ୈ
    0.36
    ulai
    0.36
    .$\
    0.36
     слабо
    0.35
     Lia
    0.35
     деталей
    0.35
    ">&
    0.35
    POSITIVE LOGITS
    wchar
    0.41
     집에
    0.40
    workspaceFolder
    0.39
     पहल
    0.38
     acredit
    0.38
    ImmediateContext
    0.38
     还
    0.38
    wyd
    0.38
    MAL
    0.38
    immediate
    0.38
    Act Density 0.004%

    No Known Activations