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

    Neuronpedia

    INDEX
    Explanations

    comparisons of equality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     buffered
    -0.07
     defaultValue
    -0.07
     reiterated
    -0.07
    spirit
    -0.06
     constitutes
    -0.06
     datasource
    -0.06
    宜
    -0.06
    _fit
    -0.06
     legislature
    -0.06
     있도록
    -0.06
    POSITIVE LOGITS
     πε
    0.07
     equally
    0.06
     roma
    0.06
     Draco
    0.06
     mercy
    0.06
     LANG
    0.06
    _BRANCH
    0.06
    Quotes
    0.06
    ่าวว
    0.06
    GD
    0.06
    Act Density 0.043%

    No Known Activations