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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SWAP
    -0.06
     kinetic
    -0.06
    usive
    -0.06
    /no
    -0.06
     setError
    -0.06
    福
    -0.06
    uncios
    -0.06
    _COLUMNS
    -0.06
    幼
    -0.06
    -/
    -0.06
    POSITIVE LOGITS
     elbows
    0.07
     зависим
    0.07
     Personality
    0.06
     стро
    0.06
     visitors
    0.06
    bum
    0.06
    itate
    0.06
    locate
    0.06
     losses
    0.06
    aims
    0.06
    Act Density 0.012%

    No Known Activations