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

    Neuronpedia

    INDEX
    Explanations

    configuration state values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etype
    0.40
    deleteOne
    0.37
    🍶
    0.37
     Wolfe
    0.36
     розта
    0.36
     locatie
    0.36
    👘
    0.36
    🎿
    0.36
    官方
    0.36
    illors
    0.36
    POSITIVE LOGITS
     έκ
    0.36
     Pursuit
    0.36
    opoietic
    0.35
     extras
    0.34
    ズル
    0.34
     హా
    0.33
     जित
    0.33
     прием
    0.33
     releases
    0.32
     Gets
    0.32
    Act Density 0.002%

    No Known Activations