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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ．
    -0.07
    "})↵
    -0.06
     nineteenth
    -0.06
     |/
    -0.06
     remember
    -0.06
     Roads
    -0.06
    “My
    -0.06
     congregation
    -0.06
     Logger
    -0.06
    ("{}
    -0.06
    POSITIVE LOGITS
    hoa
    0.07
     vòng
    0.07
    original
    0.06
    ies
    0.06
    ....↵↵
    0.06
     vrou
    0.06
    RACT
    0.06
     Surround
    0.06
    uters
    0.06
    .GetItem
    0.06
    Act Density 0.015%

    No Known Activations