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

    Neuronpedia

    INDEX
    Explanations

    orption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    朝
    -0.07
     foe
    -0.06
    ACA
    -0.06
     Ireland
    -0.06
    znám
    -0.06
    lal
    -0.06
     ulus
    -0.06
    興
    -0.06
     lia
    -0.06
     comercial
    -0.06
    POSITIVE LOGITS
     �
    0.06
    Listen
    0.06
    융
    0.06
    trx
    0.06
    limits
    0.06
     Rousse
    0.06
    ″
    0.06
    −
    0.06
     cherished
    0.06
    Standing
    0.06
    Act Density 0.000%

    No Known Activations