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

    Neuronpedia

    INDEX
    Explanations

    around

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Herz
    -0.06
     Percentage
    -0.06
    religious
    -0.06
     national
    -0.06
     genital
    -0.06
     Piper
    -0.06
     true
    -0.06
     FAILURE
    -0.06
    ª
    -0.06
     unhappy
    -0.06
    POSITIVE LOGITS
     phương
    0.07
    (article
    0.06
    zf
    0.06
    roi
    0.06
    .ask
    0.06
    quot
    0.06
    spr
    0.06
     مشاهدة
    0.06
     interpre
    0.06
     getSession
    0.06
    Act Density 0.009%

    No Known Activations