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

    Neuronpedia

    INDEX
    Explanations

    mathematical constants and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    颈
    0.51
    Очень
    0.49
     तकलीफ
    0.49
    ري
    0.47
    அ
    0.47
    ПУ
    0.46
    んです
    0.46
    مل
    0.46
    მ
    0.46
    って
    0.46
    POSITIVE LOGITS
    den
    0.52
    ch
    0.50
    Teller
    0.47
    o
    0.47
    DEN
    0.46
    per
    0.46
    '}$
    0.46
     DEN
    0.46
     친
    0.45
     water
    0.43
    Act Density 0.001%

    No Known Activations