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

    Neuronpedia

    INDEX
    Explanations

    code function names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒅁
    0.31
     Elektrokhimiya
    0.28
    橑
    0.28
    <unused237>
    0.27
     المثلثيه
    0.27
    㴬
    0.27
     phosphorylated
    0.27
     Tjiwarl
    0.26
    DUNLAND
    0.26
    MatContext
    0.26
    POSITIVE LOGITS
    ↵
    0.33
    0.32
    d
    0.31
    c
    0.31
    z
    0.29
    v
    0.29
    n
    0.29
    p
    0.29
     i
    0.28
      
    0.28
    Act Density 0.562%

    No Known Activations