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
    ]];↵
    -0.07
    ]]];↵
    -0.07
    čné
    -0.07
    .Tensor
    -0.07
     hale
    -0.07
    dB
    -0.06
    cdb
    -0.06
    .TEXT
    -0.06
     інт
    -0.06
    _LAYER
    -0.06
    POSITIVE LOGITS
     diverse
    0.06
     Caldwell
    0.06
     Former
    0.06
     یافت
    0.06
     infect
    0.06
    0.06
    �行
    0.06
    аліз
    0.06
    .DataSource
    0.06
     found
    0.06
    Act Density 0.067%

    No Known Activations