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

    Neuronpedia

    INDEX
    Explanations

    text that includes names, business titles and locations.

    oai_token-act-pair · gemini-2.0-flash

    specialized terminology or keywords in various contexts

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    IO
    -0.48
    do
    -0.47
    du
    -0.46
    ero
    -0.46
    IA
    -0.45
    p
    -0.42
    bia
    -0.42
    ub
    -0.42
    ina
    -0.41
    era
    -0.41
    POSITIVE LOGITS
    ValueStyle
    0.72
    MemoryWarning
    0.67
    Portale
    0.66
     الدولى
    0.61
    cipital
    0.60
    EndContext
    0.60
     ब्रेकडाउन
    0.60
    évaluateur
    0.59
    ủng
    0.59
    ndice
    0.59
    Act Density 5.955%

    No Known Activations