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

    Neuronpedia

    INDEX
    Explanations

    the word "in" and the phrase "number of lines"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .selenium
    -0.07
    entes
    -0.07
    zo
    -0.06
     @$_
    -0.06
    ullen
    -0.06
    dera
    -0.06
    gili
    -0.06
    ughty
    -0.06
    æĬ¬
    -0.06
     lagi
    -0.06
    POSITIVE LOGITS
     multiple
    0.12
     Multiple
    0.09
    Multiple
    0.08
    _multiple
    0.08
     several
    0.07
    multiple
    0.07
    å¤ļ
    0.07
     dozens
    0.07
     exactly
    0.06
    ivals
    0.06
    Act Density 0.129%

    No Known Activations