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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     satisfactory
    -0.07
     было
    -0.06
    测
    -0.06
     Lodge
    -0.06
    ные
    -0.06
    [it
    -0.06
     accepts
    -0.06
    ный
    -0.06
     consolation
    -0.06
    Plot
    -0.06
    POSITIVE LOGITS
     garment
    0.06
    แฟ
    0.06
     باق
    0.06
    اجات
    0.06
    PELL
    0.06
    assic
    0.06
    ереч
    0.06
     Nüfus
    0.06
    โทร
    0.06
     �
    0.06
    Act Density 0.000%

    No Known Activations