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

    Neuronpedia

    INDEX
    Explanations

    arithmetic operations and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itetty
    0.46
     सरदार
    0.40
    क्षेप
    0.40
    ensä
    0.39
    firetruck
    0.39
    ettu
    0.39
    らった
    0.38
    TextViewStyle
    0.38
    党委
    0.37
    ündung
    0.37
    POSITIVE LOGITS
    /+
    0.75
    ...+
    0.63
     +
    0.57
    /−
    0.53
     (-
    0.52
     (+)
    0.51
     n
    0.50
     k
    0.49
     (-)
    0.49
    (-)
    0.49
    Act Density 0.104%

    No Known Activations