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

    Neuronpedia

    INDEX
    Explanations

    compound words and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    饴
    0.34
     UserDao
    0.31
     pouco
    0.30
     Sacchar
    0.30
     Sereth
    0.30
    কেমিক্যাল
    0.29
    ండోత్సర్గము
    0.29
     زیرمه
    0.28
     ArrayIndex
    0.28
     Housewives
    0.28
    POSITIVE LOGITS
    -
    0.59
    с
    0.38
    −
    0.36
    _
    0.36
    а
    0.34
    ー
    0.33
    <0xF0>
    0.32
    со
    0.32
    ’
    0.32
    е
    0.31
    Act Density 0.113%

    No Known Activations