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

    Neuronpedia

    INDEX
    Explanations

    questioning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﯼ
    0.79
    Bạn
    0.77
    radians
    0.76
     mischiev
    0.74
    Hiện
    0.72
    bumptech
    0.72
    绘制
    0.71
    ្
    0.71
     orthogonality
    0.71
    hmm
    0.70
    POSITIVE LOGITS
     posed
    1.03
     Questions
    0.78
     questions
    0.77
     otáz
    0.76
     answered
    0.75
     leve
    0.74
     prompt
    0.73
    endereco
    0.71
     domande
    0.69
     leva
    0.68
    Act Density 0.347%

    No Known Activations