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

    Neuronpedia

    INDEX
    Explanations

    comparisons and advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Graph
    -0.06
     seaside
    -0.06
    intro
    -0.06
     convin
    -0.06
     defence
    -0.06
     Foreign
    -0.06
     Deck
    -0.06
     Comparative
    -0.06
    Regardless
    -0.06
     Clearly
    -0.06
    POSITIVE LOGITS
    /--
    0.07
    PART
    0.06
    /tasks
    0.06
    _sku
    0.06
    팅
    0.06
    ыш
    0.06
     mise
    0.06
    第二
    0.06
    jamin
    0.06
    ――――
    0.06
    Act Density 0.016%

    No Known Activations