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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Colonel
    -0.07
     highways
    -0.07
    ію
    -0.07
     '../../../
    -0.06
    紫
    -0.06
    خت
    -0.06
     Pa
    -0.06
     Bakan
    -0.06
     Labor
    -0.06
    'id
    -0.06
    POSITIVE LOGITS
    ださい
    0.07
     이동합니다
    0.07
     twisted
    0.06
    pector
    0.06
    itin
    0.06
    	anim
    0.06
     Pt
    0.06
     Mens
    0.06
     önemli
    0.06
    )(((
    0.06
    Act Density 0.003%

    No Known Activations