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

    Neuronpedia

    INDEX
    Explanations

    augmenting specialized labor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findBy
    0.40
    ."',
    0.39
     Faith
    0.38
    }+...+\
    0.38
    ...',
    0.38
    芽
    0.38
    Faith
    0.38
     духо
    0.38
    érience
    0.37
     为了
    0.37
    POSITIVE LOGITS
     fl
    0.42
     قادر
    0.42
     [])
    0.39
     colleg
    0.38
     IPT
    0.38
    IPT
    0.38
     Musk
    0.38
    )
    0.38
     قب
    0.37
     Milton
    0.37
    Act Density 0.005%

    No Known Activations