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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inventory
    -0.07
    INPUT
    -0.06
     ();↵↵
    -0.06
    км
    -0.06
    baseline
    -0.06
    _notify
    -0.06
    %M
    -0.06
    .getIn
    -0.06
    _path
    -0.06
    Chem
    -0.06
    POSITIVE LOGITS
     vysok
    0.07
    wishlist
    0.07
     colomb
    0.06
     воспал
    0.06
     แหล
    0.06
     répond
    0.06
    brew
    0.06
    .util
    0.06
    friendly
    0.06
     palabra
    0.06
    Act Density 0.217%

    No Known Activations