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

    Neuronpedia

    INDEX
    Explanations

    worth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ukkan
    -0.07
    .localization
    -0.07
     McK
    -0.07
     століття
    -0.06
    sockets
    -0.06
    ие
    -0.06
    ß
    -0.06
    voices
    -0.06
     chase
    -0.06
     Et
    -0.06
    POSITIVE LOGITS
    -contact
    0.07
    二十
    0.07
    aviour
    0.06
    PATH
    0.06
     dna
    0.06
     कहन
    0.06
     outfit
    0.06
    (address
    0.06
    Deployment
    0.06
     Algorithm
    0.06
    Act Density 0.009%

    No Known Activations