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

    Neuronpedia

    INDEX
    Explanations

    FG

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     test
    -0.08
     lake
    -0.08
    口水
    -0.08
     Monk
    -0.07
     Grand
    -0.07
     Rush
    -0.07
    -dollar
    -0.07
    now
    -0.07
     into
    -0.07
    폭
    -0.07
    POSITIVE LOGITS
    桲
    0.07
    혔
    0.07
    ܔ
    0.07
    أغل
    0.06
    高中生
    0.06
    딤
    0.06
    ってしまいます
    0.06
    탬
    0.06
    мат
    0.06
     doubly
    0.06
    Act Density 0.006%

    No Known Activations