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

    Neuronpedia

    INDEX
    Explanations

    and/if (conjunctions)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilarity
    -0.07
    _ios
    -0.06
     fraction
    -0.06
    (Grid
    -0.06
     mans
    -0.06
     disciple
    -0.06
     zahrani
    -0.06
    ｊ
    -0.06
    -elements
    -0.06
     좌
    -0.06
    POSITIVE LOGITS
     ут
    0.06
    Trim
    0.06
    .Format
    0.06
    UTOR
    0.06
     google
    0.06
    RESULTS
    0.06
    Storage
    0.06
    .substring
    0.06
     jon
    0.06
     Czech
    0.06
    Act Density 0.003%

    No Known Activations