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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts or specific coding elements

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

    code and random strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.51
    __':
    -0.50
    exitRule
    -0.46
    RenderAtEndOf
    -0.43
    NUMX
    -0.42
     sienta
    -0.41
    pragma
    -0.41
     jefe
    -0.41
     étrangère
    -0.40
    unanje
    -0.40
    POSITIVE LOGITS
     ASD
    0.60
    asdf
    0.60
    werty
    0.58
    EFAULT
    0.53
    ASD
    0.50
    asd
    0.48
    getDoctrine
    0.48
    djangoproject
    0.47
     GLFW
    0.46
    fillText
    0.46
    Act Density 0.008%

    No Known Activations