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

    Neuronpedia

    INDEX
    Explanations

    somewhat common English function words such as pronouns, prepositions, conjunctions, and auxillary verbs.

    oai_token-act-pair · gemini-2.0-flash

    Technical instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     <=",
    -0.59
    Merkmale
    -0.59
    lüssel
    -0.56
     WARRANT
    -0.54
     Murch
    -0.51
    ughty
    -0.50
     Theſe
    -0.50
    poran
    -0.50
     Drives
    -0.49
     gagne
    -0.49
    POSITIVE LOGITS
     force
    0.64
    VersionUID
    0.63
    force
    0.60
    DoubleQuotes
    0.59
    setupUi
    0.54
    Force
    0.52
     FORCE
    0.50
    FORCE
    0.49
    ynb
    0.47
     INTERESAR
    0.47
    Act Density 5.778%

    No Known Activations