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
     UNC
    -0.07
     ridiculous
    -0.07
     renders
    -0.07
    思考
    -0.07
     illust
    -0.07
     consumer
    -0.06
    олет
    -0.06
     able
    -0.06
     Split
    -0.06
    (`/
    -0.06
    POSITIVE LOGITS
    _bi
    0.06
    _secondary
    0.06
    eln
    0.06
    Line
    0.06
    stm
    0.06
    "><?
    0.05
    ंड
    0.05
     dictatorship
    0.05
    ===============
    0.05
    /small
    0.05
    Act Density 0.000%

    No Known Activations