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

    Neuronpedia

    INDEX
    Explanations

    hereinafter referred to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.71
     birefringence
    0.70
     egress
    0.66
    야
    0.63
    その
    0.62
    0.62
     while
    0.61
     insecurity
    0.61
     oxid
    0.60
     acceleration
    0.60
    POSITIVE LOGITS
    hereinafter
    0.91
    o
    0.85
    na
    0.79
    ль
    0.79
    aj
    0.77
    on
    0.77
    ap
    0.75
    ua
    0.74
    ai
    0.73
    is
    0.71
    Act Density 0.001%

    No Known Activations