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

    Neuronpedia

    INDEX
    Explanations

    changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ondon
    -0.07
     Collection
    -0.07
    eliminar
    -0.07
     Bank
    -0.06
    '},
    -0.06
     BANK
    -0.06
    ْ
    -0.06
     Belgian
    -0.06
     Foundation
    -0.06
     petty
    -0.06
    POSITIVE LOGITS
     changes
    0.10
     Changes
    0.09
     change
    0.08
    _except
    0.07
     uncertainty
    0.07
     сло
    0.06
    系
    0.06
    wake
    0.06
    stress
    0.06
     transition
    0.06
    Act Density 0.035%

    No Known Activations