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

    Neuronpedia

    INDEX
    Explanations

    itertools combinations permutations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sessionStorage
    0.40
    Matrix
    0.39
    Gra
    0.38
     चित्रों
    0.38
    棿
    0.38
    ulam
    0.37
     dozens
    0.36
     rendelkez
    0.35
     असंख्य
    0.35
     enumerate
    0.35
    POSITIVE LOGITS
     powdered
    0.40
     clerg
    0.39
    powder
    0.37
     poured
    0.37
    houette
    0.36
     wages
    0.36
    wci
    0.36
     pours
    0.35
    Cited
    0.35
     पनीर
    0.35
    Act Density 0.005%

    No Known Activations