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

    Neuronpedia

    INDEX
    Explanations

    cultural and political topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Doremi
    0.34
     Iterator
    0.34
     Prefecture
    0.34
    ètres
    0.34
     Omphalodes
    0.34
     רבי
    0.34
     Calyce
    0.33
     Alias
    0.32
     Firma
    0.32
    Calibration
    0.32
    POSITIVE LOGITS
     cybersecurity
    0.67
     metaverse
    0.66
     Biden
    0.66
     fintech
    0.62
     TikTok
    0.61
    Biden
    0.59
     opioids
    0.59
     billionaires
    0.59
     PFAS
    0.59
     fentanyl
    0.59
    Act Density 0.203%

    No Known Activations