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

    Neuronpedia

    INDEX
    Explanations

    phrases followed by explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SSID
    0.47
     ARIMA
    0.44
     INIS
    0.43
    ਿ
    0.43
     Modelling
    0.42
    abilidad
    0.42
     Modeling
    0.42
     Erz
    0.42
     ModInt
    0.42
     Raffa
    0.42
    POSITIVE LOGITS
    Button
    0.43
     každý
    0.42
    道的
    0.40
    很快
    0.40
     delegate
    0.40
     estimular
    0.40
    badges
    0.39
     precursor
    0.38
     سير
    0.38
     Texans
    0.38
    Act Density 0.003%

    No Known Activations