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

    Neuronpedia

    INDEX
    Explanations

    abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    S
    -1.38
    E
    -1.15
    C
    -1.12
    A
    -1.07
    T
    -1.02
    D
    -0.92
    R
    -0.88
    AAT
    -0.84
    P
    -0.81
    TTE
    -0.79
    POSITIVE LOGITS
    Personendaten
    0.70
    تقاوى
    0.68
    GEBURTSDATUM
    0.68
    ftagPool
    0.67
    EndGlobalSection
    0.66
     mergeFrom
    0.66
    IsContent
    0.64
     ujednoznacz
    0.64
    EDEFAULT
    0.64
    rrggbb
    0.63
    Act Density 0.107%

    No Known Activations