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

    Neuronpedia

    INDEX
    Explanations

    TfidfVectorizer or Tokenizer imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    positions
    0.47
    conce
    0.46
    Positions
    0.44
     positions
    0.44
    posit
    0.44
     positively
    0.42
    rel
    0.41
    concrete
    0.41
    °
    0.40
    by
    0.40
    POSITIVE LOGITS
    Tokenizer
    0.49
    聘
    0.47
    溇
    0.45
    阿拉伯
    0.42
     Strip
    0.41
    字符
    0.41
    芴
    0.41
     tokenizer
    0.40
     длина
    0.40
    ซี
    0.40
    Act Density 0.003%

    No Known Activations