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

    Neuronpedia

    INDEX
    Explanations

    derived from or based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     учетом
    0.43
     according
    0.41
    Judging
    0.40
    用于
    0.40
     sesuai
    0.39
    合う
    0.39
     selon
    0.38
    صحاب
    0.38
     Согласно
    0.37
    according
    0.37
    POSITIVE LOGITS
     derived
    1.56
    derived
    1.34
     Derived
    1.34
    Derived
    1.32
     derivative
    1.08
     dériv
    1.08
     descended
    1.07
     derivada
    1.07
     derives
    1.04
     formed
    1.03
    Act Density 0.044%

    No Known Activations