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

    Neuronpedia

    INDEX
    Explanations

    frequent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     температура
    -0.06
     hatte
    -0.06
    isci
    -0.06
     toxic
    -0.06
     Units
    -0.06
     troll
    -0.06
     існу
    -0.06
    olecules
    -0.06
    езульт
    -0.06
     но
    -0.06
    POSITIVE LOGITS
    Worksheet
    0.07
    imization
    0.06
     Cyr
    0.06
     distinctly
    0.06
     frequency
    0.06
    882
    0.06
     frequencies
    0.06
     ağ
    0.06
    ofday
    0.06
    .Typed
    0.06
    Act Density 0.009%

    No Known Activations