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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cluster
    -0.08
    集团公司
    -0.08
     Mg
    -0.08
     registrations
    -0.07
     consume
    -0.07
     concentrated
    -0.07
    长春
    -0.07
     Li
    -0.07
    ']").
    -0.07
    EF
    -0.07
    POSITIVE LOGITS
    -style
    0.08
     Seas
    0.08
     ulaş
    0.07
     бон
    0.07
    Proposal
    0.07
    opol
    0.07
     совет
    0.07
     LATIN
    0.07
    ,omitempty
    0.07
     NBC
    0.07
    Act Density 0.002%

    No Known Activations