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

    Neuronpedia

    INDEX
    Explanations

    product safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Plane
    -0.07
     RELEASE
    -0.07
     skeptic
    -0.07
     Slide
    -0.06
    blur
    -0.06
    раж
    -0.06
     Investigation
    -0.06
    yd
    -0.06
    idal
    -0.06
    Que
    -0.06
    POSITIVE LOGITS
     bied
    0.07
     dolar
    0.06
     بت
    0.06
    .processor
    0.06
     리
    0.06
    connexion
    0.06
    大阪
    0.06
     istih
    0.06
    lobber
    0.06
    Aw
    0.06
    Act Density 0.038%

    No Known Activations