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

    Neuronpedia

    INDEX
    Explanations

    abuse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     freshness
    -0.08
     QR
    -0.08
     flight
    -0.08
     precision
    -0.08
     kickoff
    -0.07
     qr
    -0.07
     signature
    -0.07
    .sig
    -0.07
     plugged
    -0.07
    soe
    -0.07
    POSITIVE LOGITS
     bullying
    0.19
     harassment
    0.17
    虐
    0.16
     violence
    0.15
     violences
    0.14
     Violence
    0.14
     violência
    0.13
     violencia
    0.13
     abusive
    0.13
     violent
    0.13
    Act Density 0.069%

    No Known Activations