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

    Neuronpedia

    INDEX
    Explanations

    list operations and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mâles
    0.39
    Fourier
    0.38
    บ่ง
    0.38
     Wellesley
    0.38
     উপকারী
    0.38
     Glaub
    0.38
     FFT
    0.37
    Norman
    0.36
     FULLER
    0.36
    枞
    0.36
    POSITIVE LOGITS
     append
    0.76
    append
    0.73
     pop
    0.70
     extend
    0.68
    pop
    0.62
    format
    0.61
     format
    0.61
    render
    0.57
     Append
    0.56
     randint
    0.54
    Act Density 0.032%

    No Known Activations