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

    Neuronpedia

    INDEX
    Explanations

    dexterity, supple, unexamined, Alfonso, Crawley

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    -3.92
    </strong>
    -2.95
    h
    -2.48
    N
    -2.28
    is
    -2.28
    ar
    -2.23
    le
    -2.20
     We
    -2.19
    z
    -2.02
     但
    -2.00
    POSITIVE LOGITS
    ’
    3.80
    ”،
    3.05
    ’，
    2.83
    🪤
    2.83
     Eigentü
    2.66
    ейчас
    2.52
    rientes
    2.50
    🦤
    2.50
     夾
    2.44
    玊
    2.44
    Act Density 0.006%

    No Known Activations