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

    Neuronpedia

    INDEX
    Explanations

    XX

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rob
    -0.07
     кораб
    -0.07
    }:
    -0.07
     Transformer
    -0.07
    Rob
    -0.07
    Foot
    -0.07
     bol
    -0.07
    _"
    -0.07
     mobil
    -0.07
    (api
    -0.07
    POSITIVE LOGITS
    XX
    0.09
    xx
    0.09
     XX
    0.07
    .xx
    0.07
     Lucy
    0.06
    070
    0.06
    eds
    0.06
     intricate
    0.06
    .ix
    0.06
    122
    0.06
    Act Density 0.004%

    No Known Activations