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

    Neuronpedia

    INDEX
    Explanations

    foreign words or scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    était
    1.21
    spaceship
    1.20
    respuesta
    1.03
    aried
    1.02
    isotropic
    1.02
    AVAILABLE
    1.01
    UREMENT
    1.00
    cookie
    1.00
    detached
    0.99
    METAL
    0.99
    POSITIVE LOGITS
    {
    1.41
    :
    1.32
     etiam
    1.21
    те
    1.20
    ই
    1.13
     cercanas
    1.09
     bubbles
    1.08
     grams
    1.05
    ↵
    1.05
     devez
    1.03
    Act Density 0.416%

    No Known Activations