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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and connecting phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    मक
    0.31
    bieter
    0.31
    盉
    0.31
    If
    0.30
    Although
    0.30
    妪
    0.30
     даже
    0.30
     поможет
    0.29
    ግዳ
    0.29
    pyridazine
    0.29
    POSITIVE LOGITS
     và
    0.36
     and
    0.35
     και
    0.34
     و
    0.34
    8
    0.34
     agus
    0.34
    0
    0.33
     lít
    0.32
     precios
    0.31
     এবং
    0.31
    Act Density 0.119%

    No Known Activations