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

    Neuronpedia

    INDEX
    Explanations

    configuration specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     WERE
    0.55
    ポール
    0.55
     RIVER
    0.55
    кистон
    0.54
    写真
    0.54
    び
    0.54
    🧇
    0.53
    役に
    0.53
    RIBUTE
    0.52
    テキスト
    0.51
    POSITIVE LOGITS
    jes
    0.53
    shakes
    0.52
    ouilles
    0.51
    hui
    0.50
    ise
    0.49
     aeruginosa
    0.49
    cs
    0.49
    oxides
    0.48
    asing
    0.48
    alities
    0.48
    Act Density 0.001%

    No Known Activations