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

    Neuronpedia

    INDEX
    Explanations

    heat and cooking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enlarged
    -0.08
    مين
    -0.07
    了一个
    -0.07
    itori
    -0.06
     earners
    -0.06
    xA
    -0.06
     Estados
    -0.06
     Africans
    -0.06
    菜肴
    -0.06
     hastily
    -0.06
    POSITIVE LOGITS
    IGNAL
    0.07
    Icon
    0.07
    价值观
    0.07
     specializing
    0.06
    (key
    0.06
    淏
    0.06
    部委
    0.06
     shredd
    0.06
    עונ
    0.06
    国土资源
    0.06
    Act Density 0.037%

    No Known Activations