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

    Neuronpedia

    INDEX
    Explanations

    set

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Canadian
    -0.06
    Canada
    -0.06
    Theory
    -0.06
     nitelik
    -0.06
    妮
    -0.06
     حضرت
    -0.06
    bled
    -0.06
     UserInfo
    -0.06
     Gron
    -0.06
    repr
    -0.06
    POSITIVE LOGITS
    ↵ ↵
    0.08
     excerpts
    0.07
    ↵
    0.06
    और
    0.06
                                  ↵
    0.06
     nossa
    0.06
    alignment
    0.06
                            ↵
    0.06
    [sub
    0.06
    )、
    0.06
    Act Density 0.002%

    No Known Activations