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

    Neuronpedia

    INDEX
    Explanations

    chess notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     katva
    0.42
     लय
    0.38
     aparel
    0.37
    primir
    0.37
    iciar
    0.37
    माइंडर
    0.37
    चर्स
    0.36
     വര്‍
    0.36
    emoration
    0.35
    jaer
    0.35
    POSITIVE LOGITS
     всех
    0.43
     Imani
    0.38
    虽然
    0.36
    localPosition
    0.36
     Residency
    0.36
     though
    0.35
    返
    0.34
    ՞
    0.34
     कैंसर
    0.33
     Costello
    0.33
    Act Density 0.001%

    No Known Activations