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

    Neuronpedia

    INDEX
    Explanations

    Constructing lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಚಿ
    0.55
     souh
    0.49
    illustrations
    0.47
    first
    0.46
     আক্রম
    0.45
     Illustrations
    0.45
    ുന്നു
    0.44
     పార్
    0.44
    striées
    0.44
     كلهم
    0.44
    POSITIVE LOGITS
    ำ
    0.49
    %
    0.48
     agrícolas
    0.46
    äder
    0.46
     discharges
    0.45
     tua
    0.45
     کاشت
    0.45
    AKE
    0.45
     sop
    0.44
    onnaise
    0.43
    Act Density 0.001%

    No Known Activations