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

    Neuronpedia

    INDEX
    Explanations

    code analysis and vulnerabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >?
    0.84
    ».
    0.80
    bcrypt
    0.78
    opengl
    0.77
    ดิน
    0.77
    Spain
    0.75
    পোষ
    0.75
    شان
    0.75
    нето
    0.73
    Portugal
    0.73
    POSITIVE LOGITS
    '
    1.04
     deprec
    0.98
     Imit
    0.84
     Dieser
    0.83
     obsol
    0.83
     Arbit
    0.83
     identifiable
    0.81
     abomin
    0.81
    ચ
    0.81
     detectable
    0.80
    Act Density 0.077%

    No Known Activations