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

    Neuronpedia

    INDEX
    Explanations

    questions and statements pertaining to definitions or explanations

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

    Text starting with "What" or "Whats"

    np_acts-logits-general · gemini-2.0-flash

    questions starting with what or how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tanleria
    -0.83
     Audiodateien
    -0.69
    ModelAdmin
    -0.65
    لكتر
    -0.65
     UnityEditor
    -0.64
     '\\;'
    -0.64
     nahilalakip
    -0.63
    EditorGUILayout
    -0.62
     незавершена
    -0.62
     насељу
    -0.61
    POSITIVE LOGITS
     EconPapers
    0.56
     différences
    0.48
     terlibat
    0.46
    __*/
    0.45
     Else
    0.45
    Why
    0.45
    why
    0.44
    เกี่ยว
    0.43
     Why
    0.43
    dekat
    0.43
    Act Density 0.085%

    No Known Activations