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

    Neuronpedia

    INDEX
    Explanations

    borders/boundaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (bt
    -0.07
     QA
    -0.07
    _reset
    -0.07
     persistence
    -0.06
    ]=(
    -0.06
    housing
    -0.06
    聞
    -0.06
    (cmd
    -0.06
    -outs
    -0.06
     @(
    -0.06
    POSITIVE LOGITS
    _BOUNDS
    0.09
    .Syntax
    0.07
     borders
    0.07
    packageName
    0.07
    _FRAME
    0.07
    _permalink
    0.06
     simmer
    0.06
    talya
    0.06
    _UTILS
    0.06
    кан
    0.06
    Act Density 0.017%

    No Known Activations