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

    Neuronpedia

    INDEX
    Explanations

    See

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    чиго
    0.38
    uale
    0.37
    rette
    0.37
    ckie
    0.37
     gle
    0.36
     trou
    0.36
     توجه
    0.36
    LEE
    0.35
    idad
    0.34
    长沙
    0.34
    POSITIVE LOGITS
    셔
    0.39
     maneuver
    0.38
    esta
    0.37
    ेस
    0.37
    িনার
    0.37
     indu
    0.37
     Shapiro
    0.37
    ramp
    0.37
    swing
    0.36
    гни
    0.35
    Act Density 0.000%

    No Known Activations