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

    Neuronpedia

    INDEX
    Explanations

    technical/academic documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     law
    -0.07
    ?",
    -0.07
    lys
    -0.07
    gefähr
    -0.07
    CHandle
    -0.07
     teasing
    -0.07
    授信
    -0.07
    之内
    -0.06
    投机
    -0.06
    投资
    -0.06
    POSITIVE LOGITS
    _rat
    0.07
     OMAP
    0.07
    -facing
    0.07
    蚰
    0.07
    袢
    0.06
     Każ
    0.06
    🇴
    0.06
    >Description
    0.06
     찾
    0.06
     statement
    0.06
    Act Density 0.026%

    No Known Activations