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

    Neuronpedia

    INDEX
    Explanations

    references to decorative elements and settings in various environments

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

    places and objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.63
    LLocation
    -0.63
     незавершена
    -0.59
     autorytatywna
    -0.59
     فريبيس
    -0.58
    RTLR
    -0.57
    featureID
    -0.57
    Rohy
    -0.57
    الدراسه
    -0.57
    ValueGenerated
    -0.56
    POSITIVE LOGITS
     referrerpolicy
    0.39
    ESTRO
    0.35
     Paese
    0.32
     tỏ
    0.32
     wireType
    0.32
     horizons
    0.31
    σία
    0.30
    lhes
    0.30
     ecco
    0.30
     milik
    0.30
    Act Density 0.019%

    No Known Activations