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

    Neuronpedia

    INDEX
    Explanations

    superlatives and references to recent experiences

    oai_token-act-pair · gemini-2.0-flash

    last

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abestanden
    -0.74
     فريبيس
    -0.67
    MLLoader
    -0.66
    ScopeManager
    -0.66
     nargin
    -0.62
    lafen
    -0.60
     purtroppo
    -0.60
     berikutnya
    -0.59
    uxxxx
    -0.59
     onFailure
    -0.58
    POSITIVE LOGITS
    RegressionTest
    0.76
    ']],
    0.65
    ();?>
    0.60
     للاسماء
    0.57
    )"),
    0.56
     #:
    0.52
     foundational
    0.52
    kable
    0.51
    ]]:
    0.51
     impactful
    0.51
    Act Density 1.470%

    No Known Activations