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
     ISS
    -0.07
    >List
    -0.06
    ,Yes
    -0.06
    .XtraGrid
    -0.06
     JSON
    -0.06
     thirteen
    -0.06
    ))*(
    -0.06
    _.
    -0.06
     λ
    -0.06
    //----------------------------------------------------------------------------↵
    -0.06
    POSITIVE LOGITS
    hold
    0.07
    очки
    0.07
    pered
    0.07
    ById
    0.07
    Watch
    0.06
    psy
    0.06
    -group
    0.06
    pit
    0.06
    าว
    0.06
    install
    0.06
    Act Density 0.758%

    No Known Activations