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

    Neuronpedia

    INDEX
    Explanations

    passive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monterey
    -0.07
    step
    -0.06
    isku
    -0.06
     count
    -0.06
     targeting
    -0.06
     ald
    -0.06
     shelter
    -0.06
     slick
    -0.06
    TODO
    -0.06
     unzip
    -0.06
    POSITIVE LOGITS
    抱
    0.07
     dbg
    0.06
     ConnectionState
    0.06
    cpy
    0.06
    这种
    0.06
     Müz
    0.06
     บาท
    0.06
     Nach
    0.06
    ←
    0.06
    ********************
    0.06
    Act Density 0.001%

    No Known Activations