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

    Neuronpedia

    INDEX
    Explanations

    web framework routing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Asian
    0.46
    UL
    0.44
    Asian
    0.40
     WASHINGTON
    0.39
     I
    0.39
    ేశ
    0.39
    US
    0.39
              
    0.39
     is
    0.39
     S
    0.38
    POSITIVE LOGITS
    to
    0.57
    드의
    0.52
    દાન
    0.49
     módulos
    0.48
    cı
    0.47
    ミノ
    0.47
    드
    0.46
    ческая
    0.45
    ığı
    0.44
    τική
    0.43
    Act Density 0.156%

    No Known Activations