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
    剐
    -0.07
    人间
    -0.07
    .speed
    -0.07
    fov
    -0.06
    怖
    -0.06
    pections
    -0.06
    \core
    -0.06
     forgive
    -0.06
     decency
    -0.06
    _SO
    -0.06
    POSITIVE LOGITS
     Spain
    0.07
    .ant
    0.07
    address
    0.07
    iolet
    0.06
    を超
    0.06
     לציין
    0.06
    ス
    0.06
     olmuştur
    0.06
    _ports
    0.06
    生活
    0.06
    Act Density 0.015%

    No Known Activations