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

    Neuronpedia

    INDEX
    Explanations

    python function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵↵
    0.48
     privados
    0.42
     prywat
    0.40
     exemplos
    0.39
     મદદ
    0.39
     DEAL
    0.39
     Private
    0.38
    Private
    0.38
     privati
    0.38
     ejemplos
    0.38
    POSITIVE LOGITS
    def
    0.51
    करने
    0.39
     으로
    0.37
    করে
    0.36
     hat
    0.36
    стива
    0.36
    $^{
    0.36
    conse
    0.35
    ᶜ
    0.35
    agnes
    0.34
    Act Density 0.004%

    No Known Activations