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

    Neuronpedia

    INDEX
    Explanations

    delegate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تش
    -0.07
     περί
    -0.07
    _msgs
    -0.07
     own
    -0.06
     detained
    -0.06
    refixer
    -0.06
    	td
    -0.06
     detention
    -0.06
    ока
    -0.06
    Stra
    -0.06
    POSITIVE LOGITS
    linkedin
    0.08
    (fullfile
    0.08
     conflic
    0.07
    _wall
    0.07
     이제
    0.07
     bozuk
    0.06
    ็กหญ
    0.06
     weap
    0.06
    imizer
    0.06
    伟
    0.06
    Act Density 0.260%

    No Known Activations