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

    Neuronpedia

    INDEX
    Explanations

    character comparison in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (bytes
    -0.06
    /tos
    -0.06
    ологія
    -0.06
     heroes
    -0.06
    _numbers
    -0.06
    Commerce
    -0.06
     يش
    -0.06
    риг
    -0.06
     radians
    -0.06
    .py
    -0.06
    POSITIVE LOGITS
    bourg
    0.07
    lid
    0.07
    Tester
    0.07
     investigated
    0.07
     Anglic
    0.06
    indy
    0.06
    <v
    0.06
     locksmith
    0.06
     meilleure
    0.06
     nord
    0.06
    Act Density 0.008%

    No Known Activations