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

    Neuronpedia

    INDEX
    Explanations

    survival, Monday, midterms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     нач
    0.65
    нер
    0.64
    ভাবে
    0.63
     gahet
    0.63
     પ્રમા
    0.63
     gleaming
    0.63
    ση
    0.63
     côn
    0.62
    ции
    0.61
     Năm
    0.61
    POSITIVE LOGITS
    at
    0.67
    هی
    0.66
    have
    0.63
    up
    0.62
    <h2>
    0.57
    ilibrium
    0.56
    and
    0.56
    ies
    0.55
    day
    0.55
    ired
    0.55
    Act Density 0.002%

    No Known Activations