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

    Neuronpedia

    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _bindings
    -0.06
    영
    -0.06
    런
    -0.06
    	Close
    -0.06
    _sent
    -0.06
    	Q
    -0.06
    ]+)/
    -0.06
     Stap
    -0.06
    equal
    -0.06
    _FWD
    -0.06
    POSITIVE LOGITS
     recon
    0.07
     chopping
    0.07
     ROI
    0.06
    懂
    0.06
    isch
    0.06
     boredom
    0.06
     Backpack
    0.06
     pancakes
    0.06
    108
    0.06
     ход
    0.06
    Act Density 0.001%

    No Known Activations