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

    Neuronpedia

    INDEX
    Explanations

    gl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]='\
    -0.65
    jectures
    -0.60
     Flo
    -0.59
    ".$_
    -0.57
    esis
    -0.56
    sheng
    -0.55
    skaya
    -0.53
     Boucher
    -0.52
    sue
    -0.51
     Google
    -0.51
    POSITIVE LOGITS
    Autoritní
    0.77
    <bos>
    0.76
    RegressionTest
    0.72
    rrggbb
    0.67
    Personensuche
    0.64
    IContainer
    0.62
     bursa
    0.62
    LookAnd
    0.60
     altar
    0.60
     Exactos
    0.60
    Act Density 0.065%

    No Known Activations