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

    Neuronpedia

    INDEX
    Explanations

    dots or periods in sentences

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

    Code snippets with "System" or CLASS

    np_acts-logits-general · gemini-2.0-flash

    code and mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     layui
    -0.72
    GEBURTSDATUM
    -0.66
    ectoria
    -0.65
    Extinguishing
    -0.64
    stateProvider
    -0.63
     ويكيميديا
    -0.62
     propOrder
    -0.59
    íferos
    -0.57
    erah
    -0.57
    RenderAtEndOf
    -0.56
    POSITIVE LOGITS
     kron
    0.53
    estens
    0.52
    accord
    0.51
     blasphemy
    0.49
     eccentricity
    0.49
     abus
    0.48
    uxxxx
    0.47
     nationalities
    0.47
     typo
    0.46
     panels
    0.46
    Act Density 0.005%

    No Known Activations