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

    Neuronpedia

    INDEX
    Explanations

    It

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     barg
    -0.08
     Boeing
    -0.08
     Associates
    -0.08
     Brokers
    -0.07
    onts
    -0.07
     প্রস
    -0.07
     Calif
    -0.07
     deft
    -0.07
    proces
    -0.07
    users
    -0.07
    POSITIVE LOGITS
     restrictions
    0.11
     제한
    0.10
     चुनौती
    0.10
     restricciones
    0.10
    限制
    0.10
     Restrictions
    0.10
     forcing
    0.10
    Constraints
    0.10
     stringent
    0.10
     handicap
    0.10
    Act Density 0.064%

    No Known Activations