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

    Neuronpedia

    INDEX
    Explanations

    mat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proteg
    1.52
    '
    1.38
     eleg
    1.37
    力
    1.34
    ?'
    1.33
    ]'
    1.33
     foc
    1.32
    :'
    1.31
     occident
    1.31
    )'
    1.30
    POSITIVE LOGITS
    ୍
    1.90
    ਟ
    1.80
    과
    1.78
    ين
    1.75
    entionally
    1.73
    й
    1.73
    на
    1.72
    ו
    1.72
    нага
    1.70
    도의
    1.66
    Act Density 0.005%

    No Known Activations