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

    Neuronpedia

    INDEX
    Explanations

    800

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ViewChild
    -0.07
    OE
    -0.07
     rocking
    -0.07
    locked
    -0.06
     Kitty
    -0.06
     partnered
    -0.06
    Disclosure
    -0.06
     CDN
    -0.06
    Santa
    -0.06
    god
    -0.06
    POSITIVE LOGITS
    (ss
    0.06
    rett
    0.06
    .Companion
    0.06
     ------>
    0.06
    AffineTransform
    0.06
    _areas
    0.06
    (`↵
    0.06
    -thumbnail
    0.06
     humiliating
    0.06
     αυ
    0.06
    Act Density 0.000%

    No Known Activations