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

    Neuronpedia

    INDEX
    Explanations

    statements and conclusions that summarize or reflect on prior information

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

    We have shown/described/demonstrated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     helico
    -0.47
    :✨
    -0.46
     Submarine
    -0.43
    */),
    -0.42
     senti
    -0.41
    inWeight
    -0.40
    NegativeButton
    -0.40
     strap
    -0.40
    quio
    -0.40
    쩌
    -0.39
    POSITIVE LOGITS
    Personendaten
    0.58
    InputBorder
    0.50
    تقاوى
    0.50
    Obrázky
    0.45
     MainAxisSize
    0.45
     AssemblyTitle
    0.43
     auguri
    0.43
    Portail
    0.42
    Geplaatst
    0.41
    клопе
    0.40
    Act Density 0.035%

    No Known Activations