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

    Neuronpedia

    INDEX
    Explanations

    fraud detection

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     `,↵
    -0.07
    .GroupBox
    -0.07
     fingerprint
    -0.07
    項目
    -0.06
    One
    -0.06
    truth
    -0.06
    sequential
    -0.06
    ROM
    -0.06
    Inter
    -0.06
     назва
    -0.06
    POSITIVE LOGITS
     Lar
    0.07
     مستق
    0.07
    ONTAL
    0.06
     agon
    0.06
     بل
    0.06
    ディース
    0.06
    .CreateInstance
    0.06
    �
    0.06
     اهل
    0.06
     postcode
    0.06
    Act Density 0.029%

    No Known Activations