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

    Neuronpedia

    INDEX
    Explanations

    decimal representation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    klassen
    0.52
    enched
    0.49
    ドル
    0.49
    τικής
    0.48
    сті
    0.47
    arıyla
    0.47
    кість
    0.47
    IntValue
    0.47
    σε
    0.46
    ття
    0.46
    POSITIVE LOGITS
     DECIMAL
    0.55
     decimal
    0.54
     Decimal
    0.52
     Located
    0.52
     It
    0.51
    decimal
    0.49
    r
    0.46
     Latina
    0.45
    m
    0.45
     साहित्य
    0.45
    Act Density 0.018%

    No Known Activations