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

    Neuronpedia

    INDEX
    Explanations

    perfect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oup
    -0.10
    ilities
    -0.09
    bbing
    -0.09
    oth
    -0.09
    ernaut
    -0.09
    734
    -0.09
    arat
    -0.09
    ertainment
    -0.09
    ernetes
    -0.09
    585
    -0.09
    POSITIVE LOGITS
    ible
    0.20
    ing
    0.18
    ibility
    0.18
    ive
    0.16
    ively
    0.16
    amente
    0.16
    fect
    0.15
    ibil
    0.15
    o
    0.15
    ors
    0.15
    Act Density 0.024%

    No Known Activations