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

    Neuronpedia

    INDEX
    Explanations

    Opinion or explanation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _income
    -0.07
     AO
    -0.07
    ичество
    -0.07
     Lagos
    -0.07
    parentNode
    -0.06
    .Special
    -0.06
     undergone
    -0.06
     można
    -0.06
     Stitch
    -0.06
     Feather
    -0.06
    POSITIVE LOGITS
     ",
    0.06
     eval
    0.06
     평가
    0.06
    (Error
    0.06
     noted
    0.06
    لیل
    0.06
    mite
    0.06
    997
    0.06
     anarch
    0.06
     discovered
    0.06
    Act Density 0.008%

    No Known Activations