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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating difficulty in understanding or finding information

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

    literature and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.63
    Geplaatst
    -0.62
     Photocase
    -0.57
    PMailer
    -0.54
    +:+
    -0.52
    ImageContext
    -0.52
    AISSEE
    -0.52
     оригіналу
    -0.51
    outSlope
    -0.51
     незавершена
    -0.51
    POSITIVE LOGITS
    Literatur
    0.43
     distinción
    0.40
    férence
    0.38
    dição
    0.38
    ásticas
    0.37
    Bibliography
    0.36
     literatura
    0.36
    férences
    0.35
    Trend
    0.35
    erías
    0.35
    Act Density 0.075%

    No Known Activations