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

    Neuronpedia

    INDEX
    Explanations

    root

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пров
    -0.08
    .JLabel
    -0.07
     consc
    -0.07
    sam
    -0.07
     ],↵
    -0.07
    -indent
    -0.06
     }],↵
    -0.06
    нин
    -0.06
     Import
    -0.06
    ltk
    -0.06
    POSITIVE LOGITS
     ειδ
    0.07
    lín
    0.07
     coppia
    0.06
     jamais
    0.06
    手
    0.06
     أك
    0.06
    omentum
    0.06
     Benghazi
    0.06
    601
    0.06
    fil
    0.06
    Act Density 0.006%

    No Known Activations