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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .BigInteger
    -0.07
    coordinates
    -0.07
     Adri
    -0.07
    ками
    -0.06
     труб
    -0.06
    source
    -0.06
    ブル
    -0.06
    Commercial
    -0.06
    -bar
    -0.06
    Markdown
    -0.06
    POSITIVE LOGITS
     ],
↵
    0.07
     income
    0.07
    ERGE
    0.06
    willReturn
    0.06
    rah
    0.06
    فع
    0.06
     бог
    0.06
    Samsung
    0.06
    emek
    0.06
     чист
    0.06
    Act Density 0.054%

    No Known Activations