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

    Neuronpedia

    INDEX
    Explanations

    statements/claims

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itos
    -0.08
     смог
    -0.07
    ____
    -0.07
    ้ำ
    -0.06
    ща
    -0.06
    زا
    -0.06
    ену
    -0.06
    rons
    -0.06
    рик
    -0.06
     cosy
    -0.06
    POSITIVE LOGITS
    ,double
    0.06
    λί
    0.06
    짝
    0.06
    (info
    0.06
     Stars
    0.06
    .toJSONString
    0.06
     prem
    0.06
    ]',↵
    0.06
    kup
    0.06
     CommandLine
    0.06
    Act Density 0.087%

    No Known Activations