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

    Neuronpedia

    INDEX
    Explanations

    Country/Region of Manufacture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StarObject
    0.41
     photoc
    0.40
    కీయ
    0.37
     AssertionError
    0.36
    纰
    0.36
    leistung
    0.35
    ibilit
    0.35
    ToDO
    0.35
     competitively
    0.35
    فس
    0.35
    POSITIVE LOGITS
     Another
    0.41
     When
    0.39
     Additionally
    0.39
     Unlike
    0.39
     Кроме
    0.39
     If
    0.38
     또
    0.38
     Although
    0.38
     また
    0.38
     如何
    0.38
    Act Density 0.000%

    No Known Activations