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

    Neuronpedia

    INDEX
    Explanations

    consequence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chambre
    -0.07
     reporters
    -0.07
     Orchestra
    -0.06
    -inspired
    -0.06
     actions
    -0.06
     classifiers
    -0.06
    JKLM
    -0.06
    Reporter
    -0.06
    $order
    -0.06
     oi
    -0.06
    POSITIVE LOGITS
    .makeText
    0.06
     �
    0.06
    大会
    0.06
     alla
    0.06
    ชอบ
    0.06
     Webb
    0.06
    かし
    0.06
    __':
↵
    0.06
    itrust
    0.06
     Phy
    0.06
    Act Density 0.013%

    No Known Activations