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

    Neuronpedia

    INDEX
    Explanations

    aspect expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    记住
    0.63
    atche
    0.55
    at
    0.54
    ats
    0.49
     Great
    0.45
     或
    0.44
    atly
    0.42
    ровать
    0.41
    atge
    0.40
    рован
    0.40
    POSITIVE LOGITS
     dystrophy
    0.48
     penyakit
    0.47
     operasi
    0.47
     Rxh
    0.47
    inserted
    0.46
    ྥ
    0.46
     minuman
    0.45
    sliding
    0.45
    DETAILS
    0.44
    일본
    0.44
    Act Density 0.002%

    No Known Activations