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

    Neuronpedia

    INDEX
    Explanations

    . key This

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     afficher
    0.49
     myCamera
    0.48
     Voir
    0.46
     [];
    0.44
     []),
    0.44
     ▶
    0.44
     []
    0.43
     mettre
    0.42
     })_{
    0.42
     être
    0.41
    POSITIVE LOGITS
    avadoc
    0.44
    ca
    0.44
    atten
    0.44
    akad
    0.43
    c
    0.43
    stad
    0.42
    ev
    0.42
    checkpoint
    0.42
    spirational
    0.41
    books
    0.41
    Act Density 0.000%

    No Known Activations