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

    Neuronpedia

    INDEX
    Explanations

    Childhelp USA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     En
    0.44
    En
    0.41
    Cleared
    0.41
    喬
    0.40
     Bradley
    0.38
    корд
    0.37
    恩
    0.36
     scala
    0.36
     Эн
    0.35
     Norm
    0.35
    POSITIVE LOGITS
    Jefferson
    0.40
     dignissimos
    0.38
    शु
    0.37
    tAux
    0.37
    Jeff
    0.37
     Jefferson
    0.35
     tack
    0.35
     Bao
    0.35
    RCP
    0.34
     Jez
    0.34
    Act Density 0.006%

    No Known Activations