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

    Neuronpedia

    INDEX
    Explanations

    State or location context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    om
    0.41
    ilio
    0.41
     ער
    0.41
    ossa
    0.40
    ge
    0.39
    issimi
    0.39
    ljen
    0.39
    ian
    0.38
    de
    0.38
    jde
    0.38
    POSITIVE LOGITS
    threads
    0.50
    ポリシー
    0.49
     distancia
    0.48
     éstas
    0.47
     sposób
    0.47
    ếm
    0.46
     fullName
    0.46
    цу
    0.46
    дагы
    0.46
     Bagaimana
    0.45
    Act Density 0.000%

    No Known Activations