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

    Neuronpedia

    INDEX
    Explanations

    references to causal conditions and assumptions in directed graphical models

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

    CFC

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.82
    出版年
    -0.80
     للمعارف
    -0.78
     صوتيه
    -0.75
    RTLR
    -0.71
     المعيارى
    -0.71
    ValueStyle
    -0.71
    áctenos
    -0.70
    rosophila
    -0.68
    Aholisi
    -0.67
    POSITIVE LOGITS
    GetCurrent
    0.46
     Gare
    0.43
    ysty
    0.38
     Grig
    0.38
     Dominic
    0.38
    Gare
    0.38
     Stur
    0.36
     ergeben
    0.35
     CFC
    0.35
    getCurrent
    0.35
    Act Density 0.662%

    No Known Activations