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

    Neuronpedia

    INDEX
    Explanations

    informational texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .band
    -0.08
     selain
    -0.08
     Trilogy
    -0.08
    ăm
    -0.07
    shade
    -0.07
    नीय
    -0.07
    .Adv
    -0.07
    _BR
    -0.07
     klo
    -0.07
    来看
    -0.07
    POSITIVE LOGITS
     disclaim
    0.08
     importantly
    0.08
     couple
    0.08
     letting
    0.08
     Tommy
    0.08
     bodily
    0.07
     اند
    0.07
    Semaphore
    0.07
     rationale
    0.07
     кредит
    0.07
    Act Density 0.096%

    No Known Activations