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

    Neuronpedia

    INDEX
    Explanations

    small

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mapper
    -0.07
     HEL
    -0.07
     fueled
    -0.07
    магаз
    -0.06
    แบ
    -0.06
     ingres
    -0.06
    ˤ
    -0.06
    プライ
    -0.06
     kas
    -0.06
    оцен
    -0.06
    POSITIVE LOGITS
    꺄
    0.07
    辖区
    0.07
    ᗢ
    0.07
    送去
    0.07
    tec
    0.07
    енд
    0.07
    lemen
    0.07
    منهج
    0.06
     erratic
    0.06
     정말
    0.06
    Act Density 0.016%

    No Known Activations