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

    Neuronpedia

    INDEX
    Explanations

    colons in scientific writing, specifically before the beginning of study-related phrases.

    oai_token-act-pair · gemini-2.0-flash

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rhestr
    -0.83
    BeginContext
    -0.80
    errHandler
    -0.77
     Мексичка
    -0.76
    المناصب
    -0.74
     contextLoads
    -0.73
    RegressionTest
    -0.73
     Majefty
    -0.73
    WithMany
    -0.72
     xenia
    -0.72
    POSITIVE LOGITS
     a
    0.76
     the
    0.66
     an
    0.57
    :
    0.50
    enor
    0.50
     It
    0.49
    ]^{\
    0.49
     Par
    0.47
     :
    0.47
     to
    0.47
    Act Density 1.772%

    No Known Activations