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

    Neuronpedia

    INDEX
    Explanations

    tiktoken and nomograms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    栋
    0.52
    もし
    0.50
    ő
    0.50
    いた
    0.49
    とにかく
    0.48
    い
    0.48
    лась
    0.48
    િત
    0.48
     الحض
    0.47
    お子
    0.47
    POSITIVE LOGITS
     antif
    0.52
     operand
    0.50
     GAS
    0.50
     spindle
    0.49
     düşük
    0.49
     burst
    0.49
     axle
    0.49
     TV
    0.48
    chev
    0.46
    esley
    0.46
    Act Density 0.000%

    No Known Activations