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

    Neuronpedia

    INDEX
    Explanations

    fragments of names and titles related to historical or geographical entities

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

    place names and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assolu
    -0.44
     attuale
    -0.41
     indietro
    -0.41
     garanzia
    -0.40
     faveur
    -0.40
     giusta
    -0.39
    écrire
    -0.39
     verità
    -0.39
     giudi
    -0.39
     leiding
    -0.39
    POSITIVE LOGITS
    تقاوى
    0.57
    WriteTagHelper
    0.55
     мәкал
    0.55
    0.51
     незавершена
    0.50
    Rüyada
    0.49
     الرياضيه
    0.48
    Derbyniad
    0.48
     bezeichneter
    0.46
    GEBURTSDATUM
    0.45
    Act Density 0.032%

    No Known Activations