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

    Neuronpedia

    INDEX
    Explanations

    unixodbc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infatti
    0.80
     Enseñ
    0.73
     정의역
    0.72
     Entonces
    0.71
    ا
    0.70
     Öncelikle
    0.70
     Benim
    0.70
     Neend
    0.68
     Antioch
    0.68
     회사
    0.64
    POSITIVE LOGITS
    0
    0.91
     to
    0.84
     with
    0.73
    with
    0.68
     अख
    0.68
     be
    0.66
    -
    0.66
    /
    0.65
     decentral
    0.65
     ف
    0.64
    Act Density 0.000%

    No Known Activations