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

    Neuronpedia

    INDEX
    Explanations

    reading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     complètes
    -0.47
    BuildContext
    -0.45
    matchCondition
    -0.45
    zám
    -0.43
     információk
    -0.43
     duquel
    -0.43
     antaranya
    -0.41
    перь
    -0.41
    erover
    -0.40
     henkil
    -0.40
    POSITIVE LOGITS
     Roskov
    0.91
    ConverterFactory
    0.71
    bootstrapcdn
    0.63
    Autoritní
    0.61
    GeneratedValue
    0.60
    hyrchwyd
    0.60
    CppCodeGen
    0.59
    ьаж
    0.59
     nomina
    0.59
    pherals
    0.58
    Act Density 0.009%

    No Known Activations