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

    Neuronpedia

    INDEX
    Explanations

    wikipedia links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘸
    0.93
    Ty
    0.83
    ങ്ങി
    0.82
    करता
    0.82
    被
    0.81
    性
    0.78
    Does
    0.77
    ワ
    0.77
     সর্ব
    0.77
     highly
    0.76
    POSITIVE LOGITS
     resultat
    0.95
     arbre
    0.87
     país
    0.83
     profund
    0.79
     proporciona
    0.78
     per
    0.77
     i
    0.76
     la
    0.76
     torna
    0.76
     pentru
    0.76
    Act Density 0.080%

    No Known Activations