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

    Neuronpedia

    INDEX
    Explanations

    indices, values, variable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Amnesty
    0.30
    服務
    0.30
    FundMe
    0.29
    expédition
    0.29
     pokuš
    0.29
     पर्यटन
    0.27
     Tây
    0.27
     अकादमी
    0.27
     профилакти
    0.27
    Công
    0.26
    POSITIVE LOGITS
     values
    0.52
    の値
    0.44
     value
    0.43
     variable
    0.43
     값이
    0.42
     string
    0.42
     numeric
    0.42
     integer
    0.41
     integers
    0.41
     hexadecimal
    0.40
    Act Density 1.680%

    No Known Activations