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

    Neuronpedia

    INDEX
    Explanations

    Chandra X-ray Observatory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commenced
    -0.07
     Newsp
    -0.07
    estruct
    -0.07
    .unlink
    -0.07
    	sb
    -0.07
     expelled
    -0.07
    以人为
    -0.07
    memo
    -0.07
    \FrameworkBundle
    -0.07
    WRAPPER
    -0.06
    POSITIVE LOGITS
     donde
    0.08
    0.07
    _PROXY
    0.07
    cream
    0.07
    _surface
    0.07
    -----↵
    0.07
    volution
    0.07
    豚
    0.07
     제가
    0.07
    roduction
    0.07
    Act Density 0.001%

    No Known Activations