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

    Neuronpedia

    INDEX
    Explanations

    legal, mathematical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IContainer
    -0.90
    ViewFeatures
    -0.89
    argout
    -0.88
    PhysRevD
    -0.82
     الاطلاع
    -0.81
     propOrder
    -0.81
    Portail
    -0.80
    Slf
    -0.80
    stdc
    -0.78
    PreferredItem
    -0.75
    POSITIVE LOGITS
    is
    0.46
    aka
    0.46
    trans
    0.44
    or
    0.43
    led
    0.43
    es
    0.42
    en
    0.42
    ne
    0.42
    ed
    0.41
    eng
    0.40
    Act Density 0.021%

    No Known Activations