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

    Neuronpedia

    INDEX
    Explanations

    ApplicationController

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ure
    0.55
    auc
    0.54
     robberies
    0.54
    t
    0.53
    ures
    0.52
    ignition
    0.52
     tremors
    0.52
     aerosols
    0.51
    above
    0.49
    falls
    0.49
    POSITIVE LOGITS
    ла
    0.84
    즈
    0.69
    ة
    0.61
    メン
    0.57
    يلي
    0.56
    مي
    0.55
    ك
    0.55
    す
    0.54
    最
    0.54
    Ꮴ
    0.54
    Act Density 0.000%

    No Known Activations