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

    Neuronpedia

    INDEX
    Explanations

    luck

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Channel
    -0.07
     biological
    -0.07
     observation
    -0.06
    기를
    -0.06
    ยก
    -0.06
     вам
    -0.06
     scooter
    -0.06
    <Application
    -0.06
     万円
    -0.06
     additional
    -0.06
    POSITIVE LOGITS
    ocket
    0.08
     texas
    0.07
     seulement
    0.07
     improbable
    0.07
     agre
    0.06
    failed
    0.06
    च
    0.06
     cler
    0.06
    Dr
    0.06
     sı
    0.06
    Act Density 0.026%

    No Known Activations