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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     등록
    -0.07
     swarm
    -0.07
     разработ
    -0.07
    .slides
    -0.07
     voc
    -0.06
    Requests
    -0.06
    ьв
    -0.06
     فار
    -0.06
     人
    -0.06
    esti
    -0.06
    POSITIVE LOGITS
    ’’
    0.07
     Crushers
    0.06
    sharp
    0.06
    ([],
    0.06
    ":↵↵
    0.06
    .detectChanges
    0.06
     panic
    0.06
     smile
    0.06
     }}
    0.06
    (View
    0.06
    Act Density 0.011%

    No Known Activations