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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    invoice
    -0.06
    grily
    -0.06
     Approximately
    -0.06
    편
    -0.06
    Glass
    -0.06
    .md
    -0.06
    的に
    -0.06
    .dump
    -0.06
     brows
    -0.06
     argue
    -0.06
    POSITIVE LOGITS
     trava
    0.08
     Alma
    0.07
    <KeyValuePair
    0.06
     Calc
    0.06
    	sys
    0.06
    steder
    0.06
    strconv
    0.06
    omanip
    0.06
    NoArgsConstructor
    0.06
     lyrics
    0.06
    Act Density 0.006%

    No Known Activations