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

    Neuronpedia

    INDEX
    Explanations

    initialisms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .puts
    -0.07
     proyecto
    -0.07
    _INV
    -0.07
     hurdles
    -0.06
     вже
    -0.06
    ९
    -0.06
    OUR
    -0.06
     WAIT
    -0.06
    .'</
    -0.06
     Dome
    -0.06
    POSITIVE LOGITS
     microbi
    0.08
    ửa
    0.07
     retir
    0.06
     Enemy
    0.06
    ši
    0.06
     reste
    0.06
    ;p
    0.06
     emin
    0.06
     Strand
    0.06
    reduce
    0.06
    Act Density 0.053%

    No Known Activations