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

    Neuronpedia

    INDEX
    Explanations

    different forms of combinations or integrations between multiple elements or factors

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

    combining multiple elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.49
    ioli
    -0.46
    racene
    -0.46
     Fibre
    -0.45
    fibre
    -0.45
    rull
    -0.45
    riors
    -0.43
     Lave
    -0.43
     Odour
    -0.43
    ratie
    -0.43
    POSITIVE LOGITS
    tangentMode
    0.54
     autorytatywna
    0.51
    sizeCache
    0.45
     defStyle
    0.45
     combinado
    0.39
     combined
    0.37
     combination
    0.36
     combinación
    0.36
     defStyleAttr
    0.35
     Վերցված
    0.35
    Act Density 0.032%

    No Known Activations