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

    Neuronpedia

    INDEX
    Explanations

    anonymous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     *"
    -0.08
     owes
    -0.07
     Ding
    -0.07
    .section
    -0.07
     ول
    -0.07
    _cu
    -0.07
    703
    -0.07
    acea
    -0.06
     Shore
    -0.06
     Well
    -0.06
    POSITIVE LOGITS
     anonymously
    0.08
     anom
    0.07
     anonym
    0.07
     anonymous
    0.07
    episode
    0.07
     anon
    0.07
     displayName
    0.07
    ович
    0.07
    Email
    0.07
    Anonymous
    0.07
    Act Density 0.004%

    No Known Activations