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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kend
    -0.07
    384
    -0.07
     MÜ
    -0.07
    _clock
    -0.07
     �
    -0.06
     Codec
    -0.06
    _CHO
    -0.06
     nick
    -0.06
    _CLOCK
    -0.06
     Themes
    -0.06
    POSITIVE LOGITS
    abbage
    0.07
     избав
    0.07
     Expected
    0.07
    委員
    0.06
     ValueError
    0.06
     halfway
    0.06
    testing
    0.06
     blockIdx
    0.06
     claiming
    0.06
    ron
    0.06
    Act Density 0.001%

    No Known Activations