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

    Neuronpedia

    INDEX
    Explanations

    Old technology and business

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     рек
    -0.07
    вержд
    -0.06
    _Delete
    -0.06
    _language
    -0.06
     ALOG
    -0.06
    fold
    -0.06
     Oriental
    -0.06
     SQUARE
    -0.06
     Beef
    -0.06
     иде
    -0.06
    POSITIVE LOGITS
     td
    0.07
    /fr
    0.06
    浮
    0.06
     filename
    0.06
    farm
    0.06
     those
    0.06
    mé
    0.06
     produce
    0.06
     fairly
    0.06
     sometimes
    0.06
    Act Density 0.133%

    No Known Activations