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

    Neuronpedia

    INDEX
    Explanations

    AV

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bed
    -0.07
    rum
    -0.07
     зуб
    -0.06
     shaved
    -0.06
     ISP
    -0.06
     fuck
    -0.06
    ưng
    -0.06
     setup
    -0.06
    _y
    -0.06
     nor
    -0.06
    POSITIVE LOGITS
    licken
    0.07
    akukan
    0.06
     Audience
    0.06
     CONNECTION
    0.06
     lords
    0.06
     '=',
    0.06
    OrderId
    0.06
    πουλος
    0.06
     Offering
    0.06
    аторы
    0.06
    Act Density 0.005%

    No Known Activations