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

    Neuronpedia

    INDEX
    Explanations

    Hiding/disabling in programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    安定
    -0.08
    褫
    -0.07
     Canary
    -0.07
     sammen
    -0.07
     conject
    -0.07
     Expect
    -0.07
    安宁
    -0.07
     super
    -0.07
     disb
    -0.07
    坚定
    -0.07
    POSITIVE LOGITS
    /templates
    0.07
    ья
    0.07
    NavBar
    0.06
    아버
    0.06
    ude
    0.06
    люб
    0.06
    /Auth
    0.06
     GIR
    0.06
     MTV
    0.06
     boots
    0.06
    Act Density 0.045%

    No Known Activations