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

    Neuronpedia

    INDEX
    Explanations

    unique

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     smrti
    -0.07
     Burnett
    -0.07
     Edwards
    -0.07
    .translate
    -0.06
    -door
    -0.06
     rail
    -0.06
     Indoor
    -0.06
    arrison
    -0.06
    ...",
    -0.06
    走
    -0.06
    POSITIVE LOGITS
     difer
    0.07
    IQ
    0.07
     Shade
    0.07
    $response
    0.07
    unique
    0.06
    (unique
    0.06
    _unique
    0.06
     Quiet
    0.06
     UInt
    0.06
     vulner
    0.06
    Act Density 0.009%

    No Known Activations