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

    Neuronpedia

    INDEX
    Explanations

    Article Titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.74
    qrstuvwxyz
    -0.69
    tagHelperRunner
    -0.65
    RegressionTest
    -0.65
    Šaltiniai
    -0.63
    baix
    -0.63
     الحره
    -0.62
    /−
    -0.62
    astéroïdes
    -0.61
     picioare
    -0.60
    POSITIVE LOGITS
    SourceChecksum
    0.43
     colspan
    0.39
    帽
    0.37
     ModelExpression
    0.35
     lain
    0.35
    הפ
    0.35
    кипедия
    0.32
     bonne
    0.32
     Matheson
    0.32
    ghest
    0.31
    Act Density 0.000%

    No Known Activations