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

    Neuronpedia

    INDEX
    Explanations

    response object followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hypothes
    0.86
    is
    0.70
     oxid
    0.69
    in
    0.67
    In
    0.63
    ोर
    0.62
     categor
    0.60
    受理
    0.59
     intensities
    0.59
     collinear
    0.55
    POSITIVE LOGITS
    ла
    0.88
     znan
    0.82
     res
    0.78
    kiej
    0.76
    الك
    0.75
    ný
    0.73
    Ź
    0.71
    ่
    0.71
     případ
    0.68
    いたり
    0.65
    Act Density 0.001%

    No Known Activations