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

    Neuronpedia

    INDEX
    Explanations

    Database partitioning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deutschland
    -0.07
     dragon
    -0.07
    spiel
    -0.07
     standard
    -0.07
     tf
    -0.06
    $',
    -0.06
    实地
    -0.06
    �
    -0.06
    甲
    -0.06
    нятие
    -0.06
    POSITIVE LOGITS
     ".");↵
    0.08
    )");
↵
    0.07
    }/{
    0.07
    زوار
    0.07
    itos
    0.07
    优选
    0.07
    Ɲ
    0.07
    .YES
    0.07
    .LayoutControlItem
    0.07
    cılı
    0.07
    Act Density 0.011%

    No Known Activations