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

    Neuronpedia

    INDEX
    Explanations

    recruiting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     التنفي
    -0.07
     النظر
    -0.07
    不见了
    -0.07
    手续
    -0.07
    ธา
    -0.07
     رسول
    -0.06
    _winner
    -0.06
    ро
    -0.06
    手臂
    -0.06
     números
    -0.06
    POSITIVE LOGITS
     Greenville
    0.08
     exotic
    0.07
     modify
    0.07
     Ether
    0.06
    {}.
    0.06
     meinen
    0.06
     referencia
    0.06
     generously
    0.06
    Mod
    0.06
     weaken
    0.06
    Act Density 0.015%

    No Known Activations