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

    Neuronpedia

    INDEX
    Explanations

    study

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     музы
    -0.08
     musical
    -0.08
     ATA
    -0.08
    encoded
    -0.08
     distracting
    -0.08
    ık
    -0.08
     distractions
    -0.08
     retreat
    -0.07
    �
    -0.07
    non
    -0.07
    POSITIVE LOGITS
     conducted
    0.12
     undertaken
    0.10
     menée
    0.10
     നടത്തിയ
    0.09
     실시
    0.09
     durchgeführt
    0.08
     _(
    0.08
     realizada
    0.08
     провед
    0.08
     conduz
    0.08
    Act Density 0.030%

    No Known Activations