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

    Neuronpedia

    INDEX
    Explanations

    last names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    led
    0.72
    also
    0.69
    while
    0.68
     annan
    0.66
     movimenti
    0.66
    ั่วโมง
    0.66
    々の
    0.65
    েই
    0.64
    randint
    0.64
     Also
    0.63
    POSITIVE LOGITS
    買って
    0.84
     utk
    0.84
     πρώτη
    0.79
    ólogo
    0.78
    otri
    0.76
    ot
    0.75
    ︠
    0.72
     dgn
    0.72
    ᓕ
    0.71
    زى
    0.70
    Act Density 0.004%

    No Known Activations