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

    Neuronpedia

    INDEX
    Explanations

    numbers and arithmetic operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒐪
    0.52
     gesprek
    0.45
     apaixon
    0.44
     Veranstaltung
    0.44
     মুক্তিফৌজ
    0.44
    𒉰
    0.44
    𒅌
    0.44
     implementación
    0.44
     nieuws
    0.43
     implementação
    0.43
    POSITIVE LOGITS
    1
    0.59
    9
    0.58
    0
    0.58
    5
    0.56
    8
    0.56
    3
    0.56
    4
    0.54
    6
    0.53
    2
    0.53
    7
    0.52
    Act Density 0.000%

    No Known Activations