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

    Neuronpedia

    INDEX
    Explanations

    India

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lemon
    0.88
     Lemon
    0.83
     wyt
    0.77
    dong
    0.77
    Treas
    0.75
     ret
    0.74
    Sophia
    0.74
    zA
    0.73
    Tucker
    0.72
     момент
    0.72
    POSITIVE LOGITS
    ریز
    0.73
    igal
    0.66
    vius
    0.66
    वॉ
    0.66
    utis
    0.66
    空気
    0.64
    kis
    0.64
     большинстве
    0.64
    ፈለ
    0.63
    抜
    0.62
    Act Density 0.000%

    No Known Activations