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

    Neuronpedia

    INDEX
    Explanations

    predicting word after positive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在
    1.14
    አ
    1.00
    も
    0.99
    In
    0.98
    và
    0.98
    ን
    0.98
    し
    0.97
    ING
    0.96
    Además
    0.96
    ל
    0.95
    POSITIVE LOGITS
    ма
    1.15
    지
    1.15
    <0x80>
    1.06
    тна
    1.05
    i
    1.02
    il
    1.02
    ิ
    1.01
     positive
    0.97
    is
    0.94
    ang
    0.94
    Act Density 0.035%

    No Known Activations