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

    Neuronpedia

    INDEX
    Explanations

    languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ót
    -0.07
    ”,
    -0.06
     exon
    -0.06
     аналіз
    -0.06
    çek
    -0.06
    ubo
    -0.06
     tur
    -0.06
    tic
    -0.06
    шин
    -0.06
     nucle
    -0.06
    POSITIVE LOGITS
    Directory
    0.08
     containment
    0.07
    /prom
    0.07
    atisf
    0.07
    assage
    0.07
    ें
    0.07
    森
    0.06
    $page
    0.06
     unmistak
    0.06
    BERS
    0.06
    Act Density 0.020%

    No Known Activations