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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ############################################################
    -0.06
    .opengl
    -0.06
     fase
    -0.06
     остров
    -0.06
    ья
    -0.06
     Держав
    -0.06
    ical
    -0.06
    (av
    -0.06
    igue
    -0.06
     졸업
    -0.06
    POSITIVE LOGITS
     تصم
    0.06
    osexual
    0.06
    -existent
    0.06
    (chr
    0.06
     sesame
    0.06
    .Allow
    0.06
     Morocco
    0.06
    irector
    0.06
     Sch
    0.06
     glow
    0.06
    Act Density 0.002%

    No Known Activations