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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ol
    -0.07
    .docs
    -0.07
     комплек
    -0.07
     sexo
    -0.07
     odst
    -0.07
     товар
    -0.07
     Вас
    -0.06
     packed
    -0.06
     Bans
    -0.06
    方式
    -0.06
    POSITIVE LOGITS
     workload
    0.06
     열
    0.06
    Digital
    0.06
     vielleicht
    0.06
    -U
    0.05
    Guy
    0.05
    (ag
    0.05
    _lst
    0.05
    company
    0.05
     теп
    0.05
    Act Density 0.001%

    No Known Activations