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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ongs
    -0.06
    ?",
    -0.06
     مؤ
    -0.06
     obed
    -0.06
    :+
    -0.06
    才
    -0.06
     Sundays
    -0.06
     sû
    -0.06
     DTO
    -0.06
    Dry
    -0.06
    POSITIVE LOGITS
     Warp
    0.06
    none
    0.06
     reliable
    0.06
     Cory
    0.06
     Image
    0.06
     Wired
    0.06
     Recomm
    0.06
    (ir
    0.06
    _Error
    0.06
    cp
    0.06
    Act Density 0.000%

    No Known Activations