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

    Neuronpedia

    INDEX
    Explanations

    grammatical explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reduction
    -0.07
     Reduction
    -0.07
     rolling
    -0.07
    .columns
    -0.07
    ét
    -0.07
    ointments
    -0.07
     CPP
    -0.07
    ICA
    -0.07
     É
    -0.07
     Escape
    -0.06
    POSITIVE LOGITS
     Residents
    0.06
     GB
    0.06
     (![
    0.06
    ΑΓ
    0.06
    /',
    0.06
     Ελλά
    0.05
     참여
    0.05
    utenant
    0.05
     PartialEq
    0.05
     úspěš
    0.05
    Act Density 0.035%

    No Known Activations