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

    Neuronpedia

    INDEX
    Explanations

    q

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Russia
    -0.07
     DOWNLOAD
    -0.07
     Baldwin
    -0.07
    rotch
    -0.06
    ушка
    -0.06
    机会
    -0.06
    -initial
    -0.06
     когда
    -0.06
     Painting
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     neglect
    0.07
    .Azure
    0.06
    lparr
    0.06
    |^
    0.06
     Ning
    0.06
     محمود
    0.06
    mute
    0.06
    oldem
    0.06
     자연
    0.06
    _ZONE
    0.06
    Act Density 0.017%

    No Known Activations