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

    Neuronpedia

    INDEX
    Explanations

    references to specific types or categories, particularly in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    single

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.50
    IntoConstraints
    -0.49
     intptr
    -0.49
    fromnode
    -0.48
    ésult
    -0.46
     StatelessWidget
    -0.45
    GEBURTSDATUM
    -0.44
    новниш
    -0.44
    viewDidLoad
    -0.42
     verbe
    -0.42
    POSITIVE LOGITS
     single
    1.21
    single
    1.15
    Single
    1.06
     Single
    1.02
     SINGLE
    0.95
    SINGLE
    0.92
     tunggal
    0.86
     singola
    0.83
    单个
    0.78
     singolo
    0.77
    Act Density 0.063%

    No Known Activations