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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gency
    -0.08
    ZY
    -0.08
     Friendly
    -0.07
     ])↵
    -0.07
    请假
    -0.07
    KG
    -0.07
    vl
    -0.07
    管理办法
    -0.07
     Wise
    -0.07
    Repeated
    -0.07
    POSITIVE LOGITS
    ᅨ
    0.07
     document
    0.06
    ﯫ
    0.06
    	Test
    0.06
    .getAll
    0.06
    ꧈
    0.06
    !("{}",
    0.06
    	side
    0.06
    ㉮
    0.06
     crippling
    0.06
    Act Density 0.091%

    No Known Activations