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

    Neuronpedia

    INDEX
    Explanations

    contract terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Flames
    -0.09
    නය
    -0.08
     Cow
    -0.08
    �
    -0.07
     ומש
    -0.07
     recorrer
    -0.07
     protege
    -0.07
     recycle
    -0.07
    алося
    -0.07
     beslut
    -0.07
    POSITIVE LOGITS
     entregar
    0.11
     subcontract
    0.10
     livré
    0.10
     stipulated
    0.10
     delivered
    0.10
     workmanship
    0.10
     entregue
    0.10
     Delivered
    0.10
     deliver
    0.09
     acceptable
    0.09
    Act Density 0.048%

    No Known Activations