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

    Neuronpedia

    INDEX
    Explanations

    topic after "the"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     están
    0.42
     were
    0.40
    s
    0.38
    ä
    0.38
    aja
    0.38
     spezielle
    0.37
    ai
    0.37
     الجديدة
    0.37
    vär
    0.37
     removing
    0.37
    POSITIVE LOGITS
     outlook
    0.45
     expectativas
    0.40
     tempo
    0.39
     tempos
    0.39
     agenda
    0.38
     fervor
    0.38
     burden
    0.37
     expectation
    0.36
     tempi
    0.36
     discourse
    0.36
    Act Density 0.178%

    No Known Activations