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

    Neuronpedia

    INDEX
    Explanations

    dates and chronological events

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

    On DATE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RefNanny
    -0.71
    InitVars
    -0.63
    AutoScaleMode
    -0.63
     OMITBAD
    -0.59
    RTEE
    -0.58
    oredCriteria
    -0.56
     BytesLike
    -0.56
     transfieras
    -0.55
     estekak
    -0.55
    الحياه
    -0.55
    POSITIVE LOGITS
    addGap
    0.35
     sportivo
    0.34
     refusé
    0.33
    AnchorTagHelper
    0.32
    addPreferredGap
    0.32
     unabhäng
    0.32
     echip
    0.31
     franceses
    0.31
     Undang
    0.31
     testigo
    0.30
    Act Density 0.061%

    No Known Activations