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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chré
    -0.55
     الرخصة
    -0.53
     françaises
    -0.53
    endforeach
    -0.51
     sauvages
    -0.50
    TemporalType
    -0.50
     colorés
    -0.50
     gratuits
    -0.49
     directs
    -0.48
    BagConstraints
    -0.48
    POSITIVE LOGITS
    ьаж
    0.65
     gainera
    0.63
    .*")]
    0.62
     Himo
    0.61
    "]();
    0.60
    anything
    0.60
     препратки
    0.60
    AsUp
    0.56
    SpringBootTest
    0.56
     anything
    0.53
    Act Density 0.103%

    No Known Activations