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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gazebo
    -0.10
     projectile
    -0.09
     कलाकार
    -0.09
     artista
    -0.08
     Projectile
    -0.08
     discs
    -0.08
    /night
    -0.08
    摄影
    -0.08
     inches
    -0.08
    收藏
    -0.08
    POSITIVE LOGITS
     underwriting
    0.11
     fintech
    0.11
     risk
    0.11
     जोखिम
    0.10
     Risk
    0.10
    .audit
    0.10
    Risk
    0.10
    风险
    0.10
     sécurisé
    0.10
    etl
    0.10
    Act Density 0.021%

    No Known Activations