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

    Neuronpedia

    INDEX
    Explanations

    release and down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Var
    0.57
    Var
    0.54
     Hr
    0.53
     kompleks
    0.53
     Köln
    0.52
     Konrad
    0.50
     Aleks
    0.50
    ój
    0.50
     Sonos
    0.50
     Sonnen
    0.49
    POSITIVE LOGITS
     markers
    0.46
    \")
    0.43
     தயாரி
    0.43
     ngại
    0.42
    ")
    0.42
     няма
    0.40
    墾
    0.39
    ಮಾಡ
    0.39
    )(&
    0.39
     ಎ
    0.38
    Act Density 0.001%

    No Known Activations