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

    Neuronpedia

    INDEX
    Explanations

    number sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aVal
    0.44
    akkan
    0.44
    university
    0.44
    uws
    0.43
    monthly
    0.42
    .}~\
    0.42
    ത്ഥ
    0.42
    compliant
    0.41
    indari
    0.41
    Ỹ
    0.41
    POSITIVE LOGITS
     .
    0.46
     Copy
    0.46
     Previous
    0.45
     Ratio
    0.44
     Upload
    0.43
     …
    0.42
     Ctrl
    0.42
     Current
    0.42
     Decimal
    0.41
     Context
    0.41
    Act Density 0.002%

    No Known Activations