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

    Neuronpedia

    INDEX
    Explanations

    Go for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    repository
    0.44
     Thanks
    0.42
     Elise
    0.42
    name
    0.41
    झा
    0.40
    协
    0.40
     систем
    0.40
    _
    0.38
     마치
    0.38
    picture
    0.38
    POSITIVE LOGITS
    小題
    0.50
     connexes
    0.46
    回來
    0.46
    voud
    0.46
     demeure
    0.46
     fouled
    0.46
    の商品は
    0.45
    istes
    0.45
    мії
    0.45
    го
    0.45
    Act Density 0.002%

    No Known Activations