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

    Neuronpedia

    INDEX
    Explanations

    understand rule foundation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     miguel
    0.48
     vila
    0.46
     renda
    0.46
     maria
    0.46
     sila
    0.45
     zespół
    0.45
     festivals
    0.45
     han
    0.45
     gorg
    0.44
    änge
    0.44
    POSITIVE LOGITS
    ૦
    0.48
    セイ
    0.47
    스
    0.46
    Bradley
    0.46
    Statement
    0.44
    ப
    0.44
    セ
    0.42
    sf
    0.42
    a
    0.42
    ان
    0.41
    Act Density 0.000%

    No Known Activations