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
     Haus
    -0.07
     ار
    -0.07
     Yönet
    -0.07
    ranking
    -0.06
     улы
    -0.06
    Marg
    -0.06
    urved
    -0.06
    _In
    -0.06
    печ
    -0.06
    _aa
    -0.06
    POSITIVE LOGITS
    .StatusInternalServerError
    0.07
    撮
    0.06
     extradition
    0.06
     drains
    0.06
     podnikatel
    0.06
     exemption
    0.06
     lief
    0.06
    _IList
    0.06
     hod
    0.06
     стак
    0.06
    Act Density 0.001%

    No Known Activations