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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.82
     radium
    -0.62
     turban
    -0.58
     torus
    -0.58
     parson
    -0.56
    Autoritní
    -0.56
    inema
    -0.55
     lugs
    -0.54
     tori
    -0.53
     baili
    -0.53
    POSITIVE LOGITS
     onOptions
    0.63
    Crossref
    0.56
     onCreateView
    0.54
    resizingMask
    0.52
    fromnode
    0.51
     ModelExpression
    0.47
    assertj
    0.47
     pedas
    0.47
    getOutputStream
    0.46
     opérés
    0.46
    Act Density 0.001%

    No Known Activations