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

    Neuronpedia

    INDEX
    Explanations

    assertion equals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _RET
    -0.07
     gost
    -0.07
    _FIRST
    -0.07
     Ethiopia
    -0.07
    EXPECT
    -0.07
    ейчас
    -0.07
     apologize
    -0.07
    .setColumns
    -0.07
    utch
    -0.07
     وهناك
    -0.06
    POSITIVE LOGITS
    待
    0.07
    移植
    0.07
     spoof
    0.07
    foobar
    0.06
     trùng
    0.06
    癖
    0.06
    itin
    0.06
    ⋎
    0.06
    ↠
    0.06
    抵抗
    0.06
    Act Density 0.003%

    No Known Activations