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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating direct relationships or impacts

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

    direct impact or effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     løpet
    -0.45
     multiuso
    -0.39
     prochaine
    -0.39
     pelbagai
    -0.38
    cellaneous
    -0.38
     mixta
    -0.37
     provisoire
    -0.37
     tendance
    -0.37
     tendances
    -0.36
    desliz
    -0.36
    POSITIVE LOGITS
     directly
    1.13
    directly
    1.10
    direct
    1.06
     direct
    1.06
    Direct
    1.05
     Directly
    1.05
    直接
    1.01
     directe
    0.91
    DIRECT
    0.91
     DIRECT
    0.90
    Act Density 0.051%

    No Known Activations