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

    Neuronpedia

    INDEX
    Explanations

    udge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    corner
    -0.07
    .apache
    -0.07
     interrupts
    -0.06
    เฉพาะ
    -0.06
    ”—
    -0.06
    >{"
    -0.06
    .preprocessing
    -0.06
    })↵↵
    -0.06
     epochs
    -0.06
     storia
    -0.06
    POSITIVE LOGITS
    udge
    0.11
     Serge
    0.07
    udging
    0.07
     Dave
    0.07
    dataTable
    0.06
     sl
    0.06
     welche
    0.06
     George
    0.06
    obar
    0.06
     Pg
    0.06
    Act Density 0.001%

    No Known Activations