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

    Neuronpedia

    INDEX
    Explanations

    simply submit and update

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    odigd
    0.42
     Also
    0.38
    ogenen
    0.38
    取り寄せ
    0.37
    hled
    0.37
    aline
    0.36
    utim
    0.36
     ['(?
    0.36
     removable
    0.36
    ânea
    0.36
    POSITIVE LOGITS
     simply
    0.64
     semplicemente
    0.63
     simplemente
    0.60
    只需
    0.58
     click
    0.57
     basta
    0.54
     klik
    0.52
     Simply
    0.52
     simplement
    0.50
    Simply
    0.50
    Act Density 0.313%

    No Known Activations