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

    Neuronpedia

    INDEX
    Explanations

    assume breach and zero trust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بيكون
    0.45
    皞
    0.43
    ologías
    0.41
     croche
    0.39
    Bibitem
    0.38
     छापे
    0.38
     revol
    0.37
    枪
    0.37
     گور
    0.37
    涩
    0.36
    POSITIVE LOGITS
    ($
    0.44
    ADOC
    0.41
     inheritance
    0.40
    liw
    0.39
     ,\
    0.39
    lf
    0.39
    users
    0.39
    (!$
    0.38
    assigned
    0.38
     Goldsmith
    0.38
    Act Density 0.004%

    No Known Activations