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

    Neuronpedia

    INDEX
    Explanations

    Scanner

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    şa
    -0.08
    AND
    -0.08
     work
    -0.07
    urally
    -0.07
    :'
    -0.07
     Lift
    -0.07
    ure
    -0.07
     THEIR
    -0.07
    裤
    -0.07
    乏力
    -0.07
    POSITIVE LOGITS
     שאנ
    0.08
    (final
    0.07
     depressing
    0.07
     совер
    0.07
    .setDate
    0.07
    Theta
    0.07
    �
    0.07
    phetamine
    0.07
     lobster
    0.07
    觎
    0.07
    Act Density 0.002%

    No Known Activations