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

    Neuronpedia

    INDEX
    Explanations

    references to writing instruments and their associated qualities

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

    writing instruments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XtraGrid
    -0.46
    inWeight
    -0.40
    Personensuche
    -0.39
    SCAR
    -0.39
    odar
    -0.39
    woof
    -0.38
     незавершена
    -0.38
    داران
    -0.37
     Vishnu
    -0.37
     visor
    -0.37
    POSITIVE LOGITS
     autorytatywna
    0.59
     writing
    0.55
     redacción
    0.54
     scrittura
    0.53
     للاسماء
    0.53
     Schreiben
    0.52
     Writing
    0.52
     Schreib
    0.50
     plumas
    0.50
     escrita
    0.49
    Act Density 0.131%

    No Known Activations