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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .upload
    -0.08
    精心
    -0.07
    Elapsed
    -0.07
    .PR
    -0.07
    "Don
    -0.07
    ׀
    -0.07
     recalling
    -0.07
     derives
    -0.07
     לפ
    -0.07
    erved
    -0.07
    POSITIVE LOGITS
    ῖ
    0.07
    CA
    0.07
    う
    0.07
    weeney
    0.07
    言い
    0.07
    �
    0.07
    fee
    0.07
    ocoder
    0.07
     Christians
    0.06
    升学
    0.06
    Act Density 0.002%

    No Known Activations