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

    Neuronpedia

    INDEX
    Explanations

    colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chloride
    -0.06
     timeout
    -0.06
    偏
    -0.06
     shortest
    -0.06
    XT
    -0.06
    atively
    -0.06
    _FT
    -0.06
     Craig
    -0.06
     containing
    -0.06
    (long
    -0.06
    POSITIVE LOGITS
     canal
    0.08
     пн
    0.06
    Jur
    0.06
     newList
    0.06
    Captain
    0.06
    mits
    0.06
    Fore
    0.06
    _gallery
    0.06
    ]:↵↵↵
    0.06
    chema
    0.06
    Act Density 0.001%

    No Known Activations