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

    Neuronpedia

    INDEX
    Explanations

    assertions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OLYBD
    0.44
    alakip
    0.44
    TST
    0.43
    rossovers
    0.42
    Scoped
    0.41
     alcoved
    0.40
     डालकर
    0.39
    incomplete
    0.39
     الشركة
    0.39
    rowse
    0.39
    POSITIVE LOGITS
    2
    0.57
     нулю
    0.54
     exacta
    0.50
    0
    0.49
     predicted
    0.48
    9
    0.48
     expected
    0.47
     situs
    0.46
    ،
    0.46
     đúng
    0.46
    Act Density 0.035%

    No Known Activations