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

    Neuronpedia

    INDEX
    Explanations

    Biographies and lifetimes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    、小
    -0.08
    谁
    -0.07
    λος
    -0.07
     |\
    -0.07
    енс
    -0.07
    ीट
    -0.07
    Slim
    -0.07
     nghiêm
    -0.07
    cretion
    -0.06
    ，所以
    -0.06
    POSITIVE LOGITS
    _FINISH
    0.06
     tackle
    0.06
    经济
    0.06
    flammatory
    0.06
     finish
    0.06
     barang
    0.05
     costa
    0.05
    ={}↵
    0.05
    six
    0.05
    .POST
    0.05
    Act Density 0.032%

    No Known Activations