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

    Neuronpedia

    INDEX
    Explanations

    })

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ỗ
    -0.07
    旋
    -0.07
    ']=$
    -0.07
     incremental
    -0.06
     хвор
    -0.06
     gallon
    -0.06
    işim
    -0.06
     vitam
    -0.06
    APPLE
    -0.06
     повіт
    -0.06
    POSITIVE LOGITS
    ,var
    0.07
    Fant
    0.07
     Α
    0.06
    िय
    0.06
     monoc
    0.06
    .FLAG
    0.06
    More
    0.06
    new
    0.06
    Ά
    0.06
     stirring
    0.06
    Act Density 0.000%

    No Known Activations