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

    Neuronpedia

    INDEX
    Explanations

    square degrees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inescapable
    0.41
     dast
    0.40
    盾
    0.39
    computed
    0.38
    ط
    0.38
    职
    0.38
    箴
    0.38
     చివరి
    0.37
    Թ
    0.37
     Лон
    0.37
    POSITIVE LOGITS
     ceremonies
    0.48
    AssemblyInfo
    0.46
    awar
    0.44
    ନ୍ତ
    0.43
    RequestMapping
    0.43
    mselves
    0.42
    ermen
    0.42
     vanno
    0.41
    ui
    0.40
     inaugurated
    0.40
    Act Density 0.002%

    No Known Activations