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

    Neuronpedia

    INDEX
    Explanations

    steps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    大学
    -0.07
     anlayış
    -0.07
    	process
    -0.07
    _activation
    -0.06
     Kepler
    -0.06
     PTSD
    -0.06
    ливих
    -0.06
    _he
    -0.06
    事
    -0.06
     kteří
    -0.06
    POSITIVE LOGITS
    Mounted
    0.06
    aved
    0.06
    KeySpec
    0.06
    (anchor
    0.06
    .twig
    0.06
     Shut
    0.06
     useCallback
    0.06
     겨
    0.06
    .XR
    0.06
                ↵↵
    0.06
    Act Density 0.024%

    No Known Activations