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

    Neuronpedia

    INDEX
    Explanations

    academic journal excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tré
    -0.26
    .pen
    -0.26
     Fraser
    -0.25
    åħ±åIJĮä½ĵ
    -0.24
     Enumerator
    -0.24
    ilda
    -0.24
    液
    -0.23
    layan
    -0.23
    nung
    -0.23
    å®ļå¾ĭ
    -0.23
    POSITIVE LOGITS
    ç¹
    0.27
    adesh
    0.25
     zar
    0.25
    urga
    0.25
    å«ļ
    0.25
    ooter
    0.24
    示èĮĥ
    0.24
    ahi
    0.24
    ilater
    0.24
    ÙĨسخ
    0.24
    Act Density 0.789%

    No Known Activations