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

    Neuronpedia

    INDEX
    Explanations

    news reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accredited
    -0.07
     Wheeler
    -0.06
     UI
    -0.06
     deposits
    -0.06
     smelling
    -0.06
     assign
    -0.06
     area
    -0.06
     Particip
    -0.06
     perpendicular
    -0.06
     Google
    -0.06
    POSITIVE LOGITS
     зобов
    0.07
     '@/
    0.07
     estos
    0.07
     ModelState
    0.07
    .deepcopy
    0.06
     Yüz
    0.06
    _next
    0.06
    .writeObject
    0.06
    .Struct
    0.06
     appDelegate
    0.06
    Act Density 0.133%

    No Known Activations