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

    Neuronpedia

    INDEX
    Explanations

    programming and tech resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ං
    0.51
    лог
    0.51
    Imidazole
    0.48
    제의
    0.45
    dolo
    0.45
    OrderFlight
    0.45
     DBox
    0.44
    ರ
    0.44
    PILE
    0.44
     返回
    0.44
    POSITIVE LOGITS
    us
    0.68
    ali
    0.63
    ab
    0.60
    ub
    0.59
    ari
    0.58
    uv
    0.58
    ag
    0.57
    az
    0.57
    s
    0.57
    f
    0.56
    Act Density 0.031%

    No Known Activations