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

    Neuronpedia

    INDEX
    Explanations

    agreement terms or parties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     buoyant
    1.46
     surging
    1.43
     towing
    1.35
     curbs
    1.31
     jurisdictional
    1.30
    侃
    1.30
    ोम
    1.27
     paraly
    1.27
     maneuvering
    1.27
    ス
    1.27
    POSITIVE LOGITS
    ä
    2.03
    ى
    2.00
    ut
    1.95
    ৫
    1.88
    ü
    1.85
    т
    1.83
    ción
    1.82
    ästä
    1.77
    ৬
    1.77
    é
    1.74
    Act Density 0.017%

    No Known Activations