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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anned
    -0.07
    垒
    -0.07
    ute
    -0.07
    explode
    -0.07
     pH
    -0.07
    inned
    -0.06
    幖
    -0.06
    第七
    -0.06
    พระราช
    -0.06
    .\
    -0.06
    POSITIVE LOGITS
    #,
    0.08
    buzz
    0.07
    該
    0.07
    /ge
    0.07
     '"'
    0.07
     Hav
    0.07
    HEY
    0.07
    終わ
    0.07
    $key
    0.06
    .emptyList
    0.06
    Act Density 0.137%

    No Known Activations