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

    Neuronpedia

    INDEX
    Explanations

    disclosure rules and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    os
    0.91
    و
    0.87
    ৩
    0.84
    ی
    0.80
    t
    0.80
    س
    0.79
    idiendo
    0.75
    ação
    0.73
    的状态
    0.73
    的速度
    0.72
    POSITIVE LOGITS
    फारिश
    0.80
     स
    0.77
     {
    0.75
    ad
    0.71
     Disclosure
    0.67
     DISCLAIM
    0.63
     beware
    0.63
    cc
    0.62
     densely
    0.62
    bs
    0.61
    Act Density 0.001%

    No Known Activations