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

    Neuronpedia

    INDEX
    Explanations

    references to comparisons and examples

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

    especially conditions or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.64
    enumi
    -0.57
    OGND
    -0.56
     חיצוניים
    -0.54
    iastes
    -0.53
    tvguidetime
    -0.52
    lgari
    -0.52
     AssemblyCulture
    -0.49
    Autoritní
    -0.49
     JADX
    -0.48
    POSITIVE LOGITS
    ConstraintMaker
    0.55
    uxxxx
    0.39
    thebibliography
    0.39
    lussen
    0.38
     mouvement
    0.35
     Haig
    0.35
     Which
    0.35
    willReturn
    0.34
    movement
    0.34
     Voulez
    0.34
    Act Density 0.127%

    No Known Activations