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

    Neuronpedia

    INDEX
    Explanations

    lack of remorse, etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Avocado
    0.53
     Egg
    0.50
     fint
    0.47
     Sugar
    0.47
     Eva
    0.46
     şeker
    0.46
     avocado
    0.46
     Aynı
    0.46
    🌺
    0.45
     your
    0.45
    POSITIVE LOGITS
    ablanca
    0.53
    ાઓ
    0.47
    AsUpIndicator
    0.44
    PositionY
    0.42
    FieldError
    0.42
     obstetric
    0.42
    ator
    0.41
    ipheral
    0.41
    อะคาเดมี
    0.41
    PRNewswire
    0.41
    Act Density 0.021%

    No Known Activations