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

    Neuronpedia

    INDEX
    Explanations

    bottom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avascript
    -0.07
     setDefaultCloseOperation
    -0.07
    nehmer
    -0.06
    -friendly
    -0.06
     jointly
    -0.06
    ]';↵
    -0.06
     numRows
    -0.06
     Finished
    -0.06
    _training
    -0.06
    	handler
    -0.06
    POSITIVE LOGITS
    weak
    0.07
     foundation
    0.07
    IPA
    0.07
     proble
    0.07
     IPL
    0.06
    hr
    0.06
     caz
    0.06
     classical
    0.06
     кора
    0.06
     derive
    0.06
    Act Density 0.024%

    No Known Activations