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

    Neuronpedia

    INDEX
    Explanations

    authentication and authorization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    -1.90
     is
    -1.59
    ?
    -1.52
     kuchen
    -1.48
    -
    -1.46
    衕
    -1.41
     budding
    -1.36
    などを
    -1.33
    3
    -1.33
    enderal
    -1.30
    POSITIVE LOGITS
    明日は
    1.45
    кономі
    1.45
    ケーション
    1.42
    𝑈
    1.40
    盈利
    1.39
    парат
    1.38
     houve
    1.37
    There
    1.35
    叕
    1.34
    ionales
    1.34
    Act Density 0.052%

    No Known Activations