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

    Neuronpedia

    INDEX
    Explanations

    news reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iná
    -0.06
    917
    -0.06
    سین
    -0.06
     aerobic
    -0.06
     먹
    -0.06
    .au
    -0.06
    Lets
    -0.06
     cassette
    -0.06
     enthusiast
    -0.06
    忙
    -0.06
    POSITIVE LOGITS
     ELEMENT
    0.08
    .drawLine
    0.07
    干
    0.07
     mistakes
    0.07
    _INVALID
    0.07
    去
    0.07
     advantages
    0.06
    .abort
    0.06
    (("
    0.06
     boils
    0.06
    Act Density 0.107%

    No Known Activations