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

    Neuronpedia

    INDEX
    Explanations

    desired or expected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     that
    -0.57
    following
    -0.50
     chrétienne
    -0.49
     Lijst
    -0.48
     a
    -0.47
     huden
    -0.45
     précé
    -0.44
     chapelle
    -0.44
     an
    -0.43
     Arrays
    -0.43
    POSITIVE LOGITS
    OrNil
    0.80
     الرياضيه
    0.76
    rawDesc
    0.75
    المناصب
    0.68
    LookAnd
    0.64
    jspx
    0.63
     NSCoder
    0.60
    "}")
    0.59
    Hentet
    0.59
    GroupLayout
    0.58
    Act Density 0.003%

    No Known Activations