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

    Neuronpedia

    INDEX
    Explanations

    What is or requires

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    represents
    0.60
    el
    0.58
    the
    0.54
    isin
    0.54
    agency
    0.54
    рки
    0.54
    v
    0.49
    ри
    0.49
    know
    0.49
    a
    0.48
    POSITIVE LOGITS
     WrestleMania
    0.48
    许可证
    0.44
     Illusion
    0.43
     Tender
    0.43
    ਊ
    0.43
     Wast
    0.42
     사용하여
    0.42
     subalgebras
    0.41
     immunosupp
    0.40
    😴
    0.40
    Act Density 0.001%

    No Known Activations