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

    Neuronpedia

    INDEX
    Explanations

    sense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     of
    -0.49
     you
    -0.47
     рода
    -0.45
     MediatR
    -0.43
    als
    -0.43
     áp
    -0.42
     sort
    -0.41
     gy
    -0.41
    둘
    -0.40
    zugehen
    -0.40
    POSITIVE LOGITS
    Chham
    0.82
    تقاوى
    0.81
     nahilalakip
    0.78
    ScopeManager
    0.70
     становника
    0.69
    RTEE
    0.68
     transfieras
    0.67
     consecration
    0.67
    iastes
    0.66
     protoimpl
    0.66
    Act Density 0.003%

    No Known Activations