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

    Neuronpedia

    INDEX
    Explanations

    squared terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     embark
    0.42
    जुर्ग
    0.39
    唿
    0.38
     discounted
    0.37
     greenery
    0.37
     commotion
    0.36
    ⤥
    0.36
     thổi
    0.36
     തൊഴിലാ
    0.36
    textured
    0.35
    POSITIVE LOGITS
     squared
    1.09
    ²
    0.98
    squared
    0.97
    ²,
    0.93
     제곱
    0.91
    ².
    0.89
     Squared
    0.84
    ²)
    0.81
    平方
    0.78
    Squared
    0.77
    Act Density 0.029%

    No Known Activations