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

    Neuronpedia

    INDEX
    Explanations

    letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рабат
    -0.07
    řik
    -0.07
    -mon
    -0.07
     Cats
    -0.07
    .acc
    -0.06
    _COMMON
    -0.06
    greso
    -0.06
    681
    -0.06
     lớn
    -0.06
     Kuwait
    -0.06
    POSITIVE LOGITS
     addslashes
    0.07
    #,
    0.07
    ∏
    0.06
     urn
    0.06
     Thurs
    0.06
    (elm
    0.06
    _CENTER
    0.06
    _Test
    0.06
    ﾆﾆﾆﾆ
    0.06
    学
    0.06
    Act Density 0.019%

    No Known Activations