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

    Neuronpedia

    INDEX
    Explanations

    divination, divinity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stral
    -0.10
    eeper
    -0.10
    /***/
    -0.09
    WER
    -0.09
     Tamb
    -0.09
    wards
    -0.09
    eda
    -0.09
    ife
    -0.09
    DSA
    -0.08
    umbing
    -0.08
    POSITIVE LOGITS
    ided
    0.20
    inity
    0.18
    isions
    0.16
    vy
    0.14
    orce
    0.14
    iders
    0.14
    (div
    0.14
    ulg
    0.13
     Div
    0.13
    ISION
    0.13
    Act Density 0.019%

    No Known Activations