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
    TYPES
    -0.08
    ظه
    -0.07
    論
    -0.07
    odge
    -0.07
    Recv
    -0.06
    aversal
    -0.06
    vasive
    -0.06
     صاح
    -0.06
     Readers
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    plier
    0.06
     trong
    0.06
     wür
    0.06
    Gab
    0.06
    $q
    0.06
    (i
    0.06
     Commod
    0.06
     состояния
    0.06
     arms
    0.06
     portions
    0.06
    Act Density 0.096%

    No Known Activations