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

    Neuronpedia

    INDEX
    Explanations

    code assignment and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lymphatiques
    0.15
    Khokhlov
    0.15
     muque
    0.14
    調理
    0.14
     jaunâtre
    0.14
    fireFlower
    0.14
     परस्मैपदी
    0.14
     mâles
    0.14
     veineux
    0.14
     fistule
    0.14
    POSITIVE LOGITS
     ((
    0.24
     (
    0.23
     get
    0.23
     Get
    0.22
    ((
    0.21
     new
    0.20
     the
    0.20
    get
    0.19
     Math
    0.19
    0.19
    Act Density 0.289%

    No Known Activations