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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Einwill
    0.93
     marchio
    0.91
     religiosas
    0.81
    DeviceCompliance
    0.81
    0.80
     caráter
    0.80
     educación
    0.80
     propietarios
    0.80
     reuniones
    0.79
    FindingsResponse
    0.78
    POSITIVE LOGITS
    ^
    1.23
    ^{
    1.19
     +
    1.10
    )^
    1.07
    ²
    1.06
    ^(
    1.02
     squared
    1.00
    /(
    0.93
     x
    0.89
    )^{
    0.87
    Act Density 0.364%

    No Known Activations