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

    Neuronpedia

    INDEX
    Explanations

    preferences and requests for assistance or help

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

    want more extra

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.69
    andExpect
    -0.52
    erçe
    -0.44
    HandlerContext
    -0.43
    succ
    -0.39
    纷
    -0.39
    ýš
    -0.39
    #+#
    -0.39
    +#+
    -0.39
     regalías
    -0.36
    POSITIVE LOGITS
     esternos
    0.42
     onCancelled
    0.41
     Exacts
    0.40
     aapt
    0.39
    LabelTagHelper
    0.37
    rdoba
    0.36
    brainly
    0.36
     ***!
    0.35
     bağlantılar
    0.35
     anonymity
    0.34
    Act Density 0.123%

    No Known Activations