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

    Neuronpedia

    INDEX
    Explanations

    mistakes and growth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Egypt
    -0.07
     необходимости
    -0.07
     />
↵
    -0.07
    (dict
    -0.07
     业
    -0.06
    Screenshot
    -0.06
    ARM
    -0.06
     یک
    -0.06
     международ
    -0.06
    (Db
    -0.06
    POSITIVE LOGITS
    егор
    0.07
     Pt
    0.06
    0.06
    414
    0.06
     gez
    0.06
     mattered
    0.06
    iday
    0.06
    SIGN
    0.06
    ashi
    0.06
    itus
    0.06
    Act Density 0.029%

    No Known Activations