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

    Neuronpedia

    INDEX
    Explanations

    being listed on a document

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     massively
    -0.07
    upro
    -0.07
    یکی
    -0.06
    嫌
    -0.06
    rende
    -0.06
    ϊκ
    -0.06
     Farage
    -0.06
    matic
    -0.06
    ภาพ
    -0.06
     explosives
    -0.06
    POSITIVE LOGITS
    assertTrue
    0.07
     çözüm
    0.07
     ;;↵
    0.06
    matrix
    0.06
    .summary
    0.06
     \<^
    0.06
     reimbursement
    0.06
    Delta
    0.06
    cen
    0.06
    made
    0.06
    Act Density 0.132%

    No Known Activations