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

    Neuronpedia

    INDEX
    Explanations

    non-English

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    flu
    0.79
    dri
    0.74
    n
    0.70
    nA
    0.70
    d
    0.69
    rally
    0.68
    u
    0.68
    fluence
    0.68
     compulsory
    0.68
     s
    0.68
    POSITIVE LOGITS
    ı
    0.89
    اعات
    0.83
    ênio
    0.81
     trabalhos
    0.80
    اعة
    0.79
    யில்
    0.78
    ээр
    0.77
     logros
    0.77
    libro
    0.75
    ivité
    0.75
    Act Density 0.000%

    No Known Activations