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

    Neuronpedia

    INDEX
    Explanations

    as of 2023

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enzymes
    0.47
    ग्रीकल्चर
    0.44
     inks
    0.43
    蘞
    0.42
     andDevice
    0.42
     setUp
    0.41
     elucid
    0.41
     archaeologist
    0.40
     orator
    0.40
     unscrupulous
    0.40
    POSITIVE LOGITS
    нар
    0.33
    務
    0.32
    估
    0.32
    Classification
    0.31
    hitung
    0.30
     कब्जे
    0.30
     جنوب
    0.30
    Guy
    0.30
     Bevölkerung
    0.30
    Thailand
    0.30
    Act Density 0.001%

    No Known Activations