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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quand
    -0.06
    rnd
    -0.06
     Translation
    -0.06
     DialogResult
    -0.06
     Hoch
    -0.06
     painful
    -0.06
     внимание
    -0.06
     что
    -0.06
     улучш
    -0.06
    Elim
    -0.06
    POSITIVE LOGITS
    -machine
    0.06
    чается
    0.06
     Token
    0.06
    tile
    0.06
     weakening
    0.06
    ていた
    0.06
    _up
    0.06
     ore
    0.06
     learning
    0.06
    ��
    0.06
    Act Density 0.265%

    No Known Activations