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

    Neuronpedia

    INDEX
    Explanations

    corruption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    無し�
    -0.07
    flows
    -0.07
    ดย
    -0.07
     Mark
    -0.07
     ActionResult
    -0.06
     Build
    -0.06
     IDs
    -0.06
    regex
    -0.06
     mark
    -0.06
     SW
    -0.06
    POSITIVE LOGITS
     Premiership
    0.07
    ipzig
    0.06
    enheim
    0.06
    <thead
    0.06
    717
    0.06
    علق
    0.06
    .listener
    0.06
     dataSource
    0.06
     wicht
    0.06
     ось
    0.06
    Act Density 0.000%

    No Known Activations