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

    Neuronpedia

    INDEX
    Explanations

    suggestions and advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _subset
    -0.09
     OPTIONAL
    -0.08
    783
    -0.08
     intrigu
    -0.08
     quintessential
    -0.08
    .strict
    -0.08
     unmistak
    -0.08
     Required
    -0.08
    Widths
    -0.08
    .Sound
    -0.08
    POSITIVE LOGITS
    等等
    0.08
     people
    0.08
     lifecycle
    0.07
    arrer
    0.07
    ，但是
    0.07
    里面
    0.07
     people's
    0.07
     oily
    0.07
     send
    0.07
     dangers
    0.07
    Act Density 3.655%

    No Known Activations