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

    Neuronpedia

    INDEX
    Explanations

    Introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    XA
    -0.07
    453
    -0.07
    -training
    -0.07
     SPF
    -0.07
    elsen
    -0.06
    SES
    -0.06
    .jsp
    -0.06
    ork
    -0.06
     Excel
    -0.06
    clone
    -0.06
    POSITIVE LOGITS
    AntiForgeryToken
    0.06
    ثمان
    0.06
    textures
    0.06
     tổ
    0.06
    readonly
    0.06
    $',
    0.06
     restaurant
    0.06
     RBI
    0.06
     "_"
    0.05
    deal
    0.05
    Act Density 0.015%

    No Known Activations