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

    Neuronpedia

    INDEX
    Explanations

    unrealistic desires, LLM, sound

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exceptionnelle
    0.50
     umowy
    0.45
     һәм
    0.45
     impegn
    0.43
     BC
    0.43
     වශ
    0.43
    بیر
    0.43
    的长
    0.42
     istilah
    0.42
     LONG
    0.41
    POSITIVE LOGITS
    1
    0.53
    ol
    0.48
    top
    0.46
    ierte
    0.45
    ulators
    0.45
    ignons
    0.44
    stage
    0.44
    z
    0.43
    ierten
    0.43
    bez
    0.43
    Act Density 0.001%

    No Known Activations