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

    Neuronpedia

    INDEX
    Explanations

    diff

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     restau
    -0.08
    Lic
    -0.07
     anderen
    -0.07
     communicates
    -0.07
    'eau
    -0.07
     Concurrent
    -0.06
    _degree
    -0.06
     menor
    -0.06
     университ
    -0.06
    _xt
    -0.06
    POSITIVE LOGITS
    鏡
    0.07
     adultos
    0.06
     wellbeing
    0.06
    iglia
    0.06
    IRS
    0.06
    زاده
    0.06
     equipo
    0.06
    ongo
    0.06
     DH
    0.06
     이미지
    0.06
    Act Density 0.015%

    No Known Activations