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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or expressions of frustration

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

    Swedish words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.84
     تضيفلها
    -0.65
    fromnode
    -0.59
     AssemblyCompany
    -0.58
     protoimpl
    -0.57
     nakalista
    -0.56
    bootstrapcdn
    -0.56
    ROIT
    -0.55
     الرياضيه
    -0.55
     Charges
    -0.55
    POSITIVE LOGITS
     kapturem
    0.40
     klubben
    0.36
     bune
    0.36
     Comprometido
    0.35
     národ
    0.35
     Unterhaltung
    0.35
     définiti
    0.34
     staden
    0.33
     Geografía
    0.33
     skolan
    0.33
    Act Density 0.009%

    No Known Activations