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

    Neuronpedia

    INDEX
    Explanations

    speech analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Levin
    -0.08
     republic
    -0.07
    Steve
    -0.07
     Nobody
    -0.07
    勇于
    -0.07
    .readline
    -0.06
     `"
    -0.06
     ARM
    -0.06
    CHECK
    -0.06
     WALL
    -0.06
    POSITIVE LOGITS
     picker
    0.07
     mats
    0.07
    ATT
    0.07
    جي
    0.07
     추
    0.06
    Ж
    0.06
    🏋
    0.06
    'e
    0.06
    slice
    0.06
     ";
↵
    0.06
    Act Density 0.032%

    No Known Activations