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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     :=↵
    -0.06
    Theo
    -0.06
    .objects
    -0.06
    ریان
    -0.06
    iterator
    -0.06
    andas
    -0.06
    roll
    -0.06
     яка
    -0.06
     masterpiece
    -0.06
    ροφορίες
    -0.06
    POSITIVE LOGITS
     зни
    0.07
     SCI
    0.06
    .trip
    0.06
     사람이
    0.06
     Pradesh
    0.06
    ถาน
    0.06
    ΕΧ
    0.06
    abelle
    0.06
    245
    0.06
    ностей
    0.06
    Act Density 0.169%

    No Known Activations