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

    Neuronpedia

    INDEX
    Explanations

    s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setPreferred
    0.32
    bracelet
    0.29
    whereas
    0.29
    adding
    0.29
    resonance
    0.29
    adjustable
    0.28
     Abbreviations
    0.27
    acceptable
    0.27
     alternativa
    0.27
     مکمل
    0.27
    POSITIVE LOGITS
     сначала
    0.31
     reasons
    0.30
     бекер
    0.30
    的原因
    0.30
    aund
    0.30
    理由は
    0.30
     शंक
    0.29
     simply
    0.29
     ctx
    0.29
     discharge
    0.28
    Act Density 0.032%

    No Known Activations