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

    Neuronpedia

    INDEX
    Explanations

    highly significant numerical or statistical values

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

    Radial Engineering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.98
    AddTagHelper
    -0.78
    GOTREF
    -0.73
    AddHtmlAttribute
    -0.63
    AnchorStyles
    -0.62
    angelog
    -0.61
    findpost
    -0.60
    WriteTagHelper
    -0.60
    ConstraintMaker
    -0.59
    ValueStyle
    -0.59
    POSITIVE LOGITS
     terms
    0.32
     shot
    0.32
     adel
    0.31
    INCREF
    0.31
     SPL
    0.31
     rates
    0.31
    sys
    0.30
    pso
    0.30
     principle
    0.30
    houd
    0.30
    Act Density 0.000%

    No Known Activations