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

    Neuronpedia

    INDEX
    Explanations

    speed or intensity levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Komponenten
    0.53
     components
    0.47
    malıdır
    0.46
    .$(
    0.46
     componenti
    0.45
    Components
    0.45
    変数
    0.45
     componentes
    0.44
    Component
    0.44
     Änderung
    0.44
    POSITIVE LOGITS
     或
    0.53
    你会
    0.47
    hkse
    0.45
    你应该
    0.44
     ለአ
    0.43
    你會
    0.43
     στις
    0.43
     GL
    0.43
     स्टार्ट
    0.42
     开始
    0.42
    Act Density 0.009%

    No Known Activations