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
    GreaterThan
    -0.07
     sco
    -0.07
    같
    -0.07
     출력
    -0.06
     yên
    -0.06
     sexe
    -0.06
     steak
    -0.06
     Steak
    -0.06
    ्रच
    -0.06
    hpp
    -0.06
    POSITIVE LOGITS
    usunda
    0.07
     (_.
    0.07
     �
    0.06
     magnificent
    0.06
     (_
    0.06
    форм
    0.06
    #"
    0.06
     katıl
    0.06
    ως
    0.06
    appiness
    0.06
    Act Density 0.000%

    No Known Activations