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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()['
    -0.07
    imiters
    -0.06
    _bg
    -0.06
    .images
    -0.06
    .alpha
    -0.06
    rál
    -0.06
    现场
    -0.06
    .getZ
    -0.06
     alive
    -0.06
     cassette
    -0.06
    POSITIVE LOGITS
     venda
    0.07
     OutlineInputBorder
    0.06
    675
    0.06
    tron
    0.06
    invest
    0.06
    Ce
    0.06
     creampie
    0.06
     MOVE
    0.06
     undisclosed
    0.05
     EVER
    0.05
    Act Density 0.067%

    No Known Activations