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

    Neuronpedia

    INDEX
    Explanations

    legal and procedural terminology

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

    quantity or multiple entities

    np_acts-logits-general · gemini-2.0-flash

    multi-word phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.97
    sizeCache
    -0.83
     createSlice
    -0.79
     дописавши
    -0.79
     CreateTagHelper
    -0.76
     Efq
    -0.74
    下载附件
    -0.73
    Jeografia
    -0.72
     Мексичка
    -0.69
     Shaksp
    -0.68
    POSITIVE LOGITS
     many
    0.64
     certaines
    0.64
     certains
    0.63
     egyik
    0.61
     некоторых
    0.60
     some
    0.58
     most
    0.56
    いくつか
    0.55
    หลาย
    0.54
     algunos
    0.54
    Act Density 0.599%

    No Known Activations