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

    Neuronpedia

    INDEX
    Explanations

    easy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oursquare
    0.59
    Warning
    0.58
    varian
    0.57
     Warning
    0.56
     buruk
    0.55
    ULD
    0.55
     मुकेश
    0.55
    堝
    0.53
    WARNING
    0.53
     Unknown
    0.53
    POSITIVE LOGITS
     easy
    5.52
    Easy
    4.95
    easy
    4.93
     Easy
    4.91
     easier
    4.83
     fácil
    4.62
     easily
    4.38
     EASY
    4.34
     fáciles
    4.25
     easiest
    4.15
    Act Density 1.374%

    No Known Activations