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

    Neuronpedia

    INDEX
    Explanations

    important terms and concepts related to design and creativity

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

    feature story

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.71
     ویکی‌پدی
    -0.71
    Datuak
    -0.65
    protoimpl
    -0.63
    expandindo
    -0.55
    __":
    -0.54
    évaluateur
    -0.54
    Portály
    -0.53
     дописавши
    -0.53
     estekak
    -0.53
    POSITIVE LOGITS
    ској
    0.52
     kick
    0.51
     holes
    0.48
     body
    0.47
     hyper
    0.47
     park
    0.46
     job
    0.46
     hem
    0.45
     yearly
    0.45
     pit
    0.45
    Act Density 0.051%

    No Known Activations