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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    forward
    -0.07
    ordova
    -0.07
    istros
    -0.07
    ΩΤ
    -0.06
    .permissions
    -0.06
    .args
    -0.06
    washer
    -0.06
    unused
    -0.06
     mosques
    -0.06
    olar
    -0.06
    POSITIVE LOGITS
    _added
    0.06
     tiene
    0.06
    ексу
    0.06
     blinded
    0.06
     ثبت
    0.06
     being
    0.06
    相
    0.06
     छ
    0.06
    ρθρο
    0.06
    ceipt
    0.06
    Act Density 0.007%

    No Known Activations