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

    Neuronpedia

    INDEX
    Explanations

    Celsius Fahrenheit scales

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kannya
    0.60
    髏
    0.55
     puree
    0.52
    ς
    0.52
    bamos
    0.52
    kast
    0.52
    issaient
    0.52
    nę
    0.51
     burdensome
    0.51
    naments
    0.51
    POSITIVE LOGITS
    in
    0.93
    temperature
    0.90
    ف
    0.80
    ра
    0.78
    as
    0.78
     Temperature
    0.75
     Temperaturen
    0.75
    ка
    0.75
    Temperature
    0.73
     Fahrenheit
    0.71
    Act Density 0.011%

    No Known Activations