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

    Neuronpedia

    INDEX
    Explanations

    references to specific items or experiences, particularly those mentioned with "this."

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

    this manual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalTable
    -0.65
     дописавши
    -0.52
     محفوظة
    -0.52
     BoxFit
    -0.49
    URLException
    -0.48
     unknownFields
    -0.47
     kasarigan
    -0.46
    awtextra
    -0.44
    LayoutStyle
    -0.44
    tonode
    -0.43
    POSITIVE LOGITS
    とにかく
    0.37
     withRouter
    0.37
    Péri
    0.36
    enetrable
    0.34
     ujednoznacz
    0.34
     MediatR
    0.33
     moteur
    0.32
    reportWebVitals
    0.32
     cref
    0.32
     gutters
    0.32
    Act Density 0.003%

    No Known Activations