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

    Neuronpedia

    INDEX
    Explanations

    descriptive qualities and aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isely
    0.47
    voorbeeld
    0.39
    ），
    0.38
    用于
    0.38
     অথবা
    0.38
     Apache
    0.37
     importantly
    0.36
     Tidak
    0.36
     Beautiful
    0.36
    ற்காக
    0.36
    POSITIVE LOGITS
     confines
    0.54
     intricacies
    0.53
     workings
    0.50
     nature
    0.45
    ness
    0.44
     complexities
    0.43
     expanse
    0.42
     nuances
    0.39
     totality
    0.38
     portions
    0.38
    Act Density 0.344%

    No Known Activations