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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ReadByte
    -0.07
     IReadOnly
    -0.06
     δύ
    -0.06
    ερμαν
    -0.06
    ॉन
    -0.06
     GOOGLE
    -0.06
    _BAR
    -0.06
     deployed
    -0.06
    	freopen
    -0.06
    üslüman
    -0.06
    POSITIVE LOGITS
     Baz
    0.07
    shed
    0.07
    .Transform
    0.07
    养
    0.06
    众
    0.06
     Subjects
    0.06
    odox
    0.06
    .Exception
    0.06
     Mask
    0.06
     Environment
    0.06
    Act Density 0.012%

    No Known Activations