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

    Neuronpedia

    INDEX
    Explanations

    free

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ModifiedDate
    -0.07
     Salary
    -0.07
     architectural
    -0.07
     �
    -0.07
     consistent
    -0.07
    Cr
    -0.07
     defence
    -0.07
    department
    -0.07
     Sci
    -0.07
    War
    -0.06
    POSITIVE LOGITS
     assort
    0.07
    xxxxxxxx
    0.06
    _tc
    0.06
     피해
    0.06
    вою
    0.06
    诉
    0.06
    巴
    0.06
     obraz
    0.06
     클래스
    0.06
     вида
    0.06
    Act Density 0.000%

    No Known Activations