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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Until
    -0.08
    Ｑ
    -0.07
    "}),↵
    -0.07
    ú
    -0.07
    atto
    -0.07
     Delta
    -0.07
    たら
    -0.06
    sn
    -0.06
    inclusive
    -0.06
    izzare
    -0.06
    POSITIVE LOGITS
     cumshot
    0.08
    .goBack
    0.07
     removeFrom
    0.07
    队员们
    0.07
    -shopping
    0.07
    鹇
    0.07
    prefix
    0.07
    紋
    0.07
    打印机
    0.07
    .showError
    0.07
    Act Density 0.001%

    No Known Activations