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

    Neuronpedia

    INDEX
    Explanations

    Shadow, Yasuo, vulnerability, language select

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    馆
    0.40
    स्ड
    0.39
    үн
    0.38
     ہمیشہ
    0.38
     séries
    0.38
     PML
    0.37
    ന്ത
    0.37
    څ
    0.37
     inseg
    0.36
     بیٹھ
    0.36
    POSITIVE LOGITS
    select
    0.38
    ardini
    0.38
     X
    0.38
    def
    0.37
     Enforcement
    0.37
    afi
    0.37
     Brazil
    0.37
     Nebula
    0.37
     Cornerstone
    0.37
     x
    0.36
    Act Density 0.000%

    No Known Activations