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

    Neuronpedia

    INDEX
    Explanations

    power rule and derivatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thirteen
    0.45
    ającym
    0.45
     ይህም
    0.44
    र्यंत
    0.44
    ፤
    0.43
    ၆
    0.43
    listings
    0.43
    łę
    0.43
    焊
    0.43
    ሏ
    0.42
    POSITIVE LOGITS
     sencillo
    0.53
     Element
    0.51
     Substituting
    0.51
     Substitute
    0.50
     -=
    0.49
     substituted
    0.49
     substituting
    0.49
     compon
    0.49
     Rule
    0.48
     Answer
    0.47
    Act Density 0.014%

    No Known Activations