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

    Neuronpedia

    INDEX
    Explanations

    look away

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ar
    1.83
    ز
    1.75
    ️
    1.75
    JOptionPane
    1.72
     Bewertung
    1.65
    oor
    1.63
    žite
    1.61
    %>%
    1.59
    েল
    1.58
    க்கால்
    1.57
    POSITIVE LOGITS
    𝖙
    1.76
    𝖑
    1.68
     maniac
    1.66
    ही
    1.62
     plurality
    1.62
     affairs
    1.61
     leta
    1.61
    remely
    1.60
     prophets
    1.60
    τών
    1.60
    Act Density 0.000%

    No Known Activations