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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     клад
    -0.06
     descendants
    -0.06
    820
    -0.06
     İki
    -0.06
     Pictures
    -0.06
    ，用
    -0.06
    ذه
    -0.06
    aurant
    -0.06
    ########################
    -0.06
    这么
    -0.06
    POSITIVE LOGITS
    -helper
    0.07
     мар
    0.06
     superClass
    0.06
     localStorage
    0.06
    >;↵↵
    0.06
    Tasks
    0.06
    HEEL
    0.06
     Hot
    0.06
     financial
    0.06
     عدم
    0.06
    Act Density 0.007%

    No Known Activations