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

    Neuronpedia

    INDEX
    Explanations

    apostrophe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('~
    -0.07
     브라
    -0.06
     Beef
    -0.06
     weitere
    -0.06
     '"
    -0.06
    $k
    -0.06
    三个
    -0.06
    _MISSING
    -0.06
    tbody
    -0.06
     BUFFER
    -0.06
    POSITIVE LOGITS
    ็จพระ
    0.07
    лату
    0.07
    bufio
    0.07
    olum
    0.06
     chatt
    0.06
     McCart
    0.06
    _digits
    0.06
    ษ
    0.06
    Way
    0.06
     řešení
    0.06
    Act Density 0.004%

    No Known Activations