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

    Neuronpedia

    INDEX
    Explanations

    scientific data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nul
    -0.07
     تیم
    -0.07
    ��
    -0.07
     ا�
    -0.06
    ;/
    -0.06
    継
    -0.06
    ipa
    -0.06
    MOV
    -0.06
     سه
    -0.06
     ตร
    -0.06
    POSITIVE LOGITS
    (arguments
    0.07
    .Int
    0.07
     Halifax
    0.06
    .Consumer
    0.06
    щин
    0.06
    .Grid
    0.06
    .Interface
    0.06
     MacDonald
    0.06
     Lloyd
    0.06
     Assassin
    0.05
    Act Density 0.001%

    No Known Activations