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

    Neuronpedia

    INDEX
    Explanations

    allowed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Advisor
    -0.08
    �
    -0.08
     deposito
    -0.08
    ੁਰੂ
    -0.07
     impactful
    -0.07
     Mr
    -0.07
     Consultant
    -0.07
     Mest
    -0.07
     Depos
    -0.07
     Brilliant
    -0.07
    POSITIVE LOGITS
     estadísticas
    0.09
    Gap
    0.09
     defenses
    0.09
     название
    0.08
    Official
    0.08
     slogan
    0.08
     conceded
    0.08
    Grammar
    0.08
     WH
    0.08
     gemiddeld
    0.08
    Act Density 0.021%

    No Known Activations