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

    Neuronpedia

    INDEX
    Explanations

    inaccuracies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trump
    -0.08
    ),↵↵
    -0.08
    Active
    -0.07
     kl
    -0.07
     estud
    -0.07
     auctions
    -0.07
    ARP
    -0.07
    .Err
    -0.06
    淹没
    -0.06
    ผลกระท
    -0.06
    POSITIVE LOGITS
    更深
    0.07
    因为她
    0.07
    rends
    0.06
    olicies
    0.06
    보다
    0.06
     =================================================
    0.06
    JoinColumn
    0.06
    PARAM
    0.06
    ובת
    0.06
     REGISTER
    0.06
    Act Density 0.113%

    No Known Activations