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

    Neuronpedia

    INDEX
    Explanations

    seem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     utilities
    -0.07
     Woo
    -0.07
     Tops
    -0.07
     gems
    -0.07
    day
    -0.07
    재
    -0.06
     injuries
    -0.06
    PAR
    -0.06
     SVM
    -0.06
    -bar
    -0.06
    POSITIVE LOGITS
     gerçekleştir
    0.07
    .Struct
    0.06
    .startActivity
    0.06
     através
    0.06
    меч
    0.06
     unpopular
    0.06
    destruct
    0.06
     SHR
    0.06
     inputStream
    0.06
    inform
    0.06
    Act Density 0.008%

    No Known Activations