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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers or codes related to data or entries

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

    Mathematical or scientific formulas/equations

    np_acts-logits-general · gemini-2.0-flash

    code snippets and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     things
    -0.57
    ↵↵
    -0.54
     people
    -0.54
     thing
    -0.52
     beautiful
    -0.51
     folks
    -0.50
     you
    -0.49
     #
    -0.48
     way
    -0.47
     cosas
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.97
     estekak
    0.82
    localctx
    0.77
     صوتيه
    0.74
    AccessorTable
    0.73
     GenerationType
    0.73
    elemField
    0.73
     $_"
    0.72
    transQ
    0.71
    __":
    0.70
    Act Density 0.490%

    No Known Activations