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

    Neuronpedia

    INDEX
    Explanations

    voice and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     valeurs
    0.56
    wertung
    0.55
     erreichen
    0.51
     Locals
    0.50
     Krause
    0.50
     lernen
    0.49
     Galerie
    0.49
     Avec
    0.49
     Relations
    0.48
     malé
    0.48
    POSITIVE LOGITS
    music
    0.55
    hears
    0.54
    ności
    0.52
    մ
    0.51
    noise
    0.50
    ady
    0.50
    azir
    0.50
    לו
    0.49
    imon
    0.49
    iram
    0.49
    Act Density 0.000%

    No Known Activations