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

    Neuronpedia

    INDEX
    Explanations

    malicious code or attacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expires
    0.41
     ஐந்து
    0.39
    refined
    0.39
    雲
    0.39
     continuance
    0.39
    authority
    0.38
     रिपीट
    0.38
     fillColorSpace
    0.38
     volunt
    0.38
    ূন্য
    0.38
    POSITIVE LOGITS
     FEM
    0.43
     Μ
    0.41
     Рі
    0.39
    }=\
    0.39
     Ми
    0.37
                         
    0.37
     Loki
    0.37
     Mà
    0.36
     ప్రి
    0.36
     beet
    0.36
    Act Density 0.000%

    No Known Activations