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

    Neuronpedia

    INDEX
    Explanations

    the presence of structural markers or elements in a document

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

    Immediately before numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.74
     tartalomajánló
    -0.72
    PyExc
    -0.72
    AccessorTable
    -0.70
    esModule
    -0.70
    TagMode
    -0.67
    ніципа
    -0.65
    DrawerToggle
    -0.65
    omials
    -0.65
    ]<<"
    -0.64
    POSITIVE LOGITS
     climati
    0.54
     puzzle
    0.51
    好感
    0.50
    Elsewhere
    0.49
     Celui
    0.48
     interac
    0.46
     located
    0.46
    Localisation
    0.46
     boss
    0.45
     coffre
    0.44
    Act Density 0.210%

    No Known Activations