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

    Neuronpedia

    INDEX
    Explanations

    excessive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -away
    -0.08
     stirred
    -0.07
     willing
    -0.07
    _down
    -0.06
     misunderstanding
    -0.06
     likely
    -0.06
     pull
    -0.06
     able
    -0.06
     puzzles
    -0.06
     jump
    -0.06
    POSITIVE LOGITS
     excessive
    0.15
    cessive
    0.13
     excessively
    0.10
     aşırı
    0.07
    =:
    0.07
    dr
    0.07
     overly
    0.07
    ie
    0.07
    щи
    0.07
    IC
    0.07
    Act Density 0.006%

    No Known Activations