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

    Neuronpedia

    INDEX
    Explanations

    java or objective-c code

    oai_token-act-pair · gemini-2.0-flash

    code punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.88
    цездатний
    -0.81
    NameInMap
    -0.80
     дописавши
    -0.73
     للاسماء
    -0.73
    saraba
    -0.72
    writeFieldEnd
    -0.68
     EconPapers
    -0.67
     noqa
    -0.65
     &___
    -0.65
    POSITIVE LOGITS
     Liefer
    0.45
    wpdb
    0.45
     coucher
    0.42
    "")
    0.41
    ASONS
    0.40
    wachs
    0.40
    vection
    0.39
    vium
    0.39
    %"
    0.39
    کنندگان
    0.39
    Act Density 0.381%

    No Known Activations