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

    Neuronpedia

    INDEX
    Explanations

    social-emotional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Orb
    -0.08
    plane
    -0.07
     orb
    -0.07
    romy
    -0.07
     plane
    -0.07
     inconvenience
    -0.07
     Wife
    -0.07
    wife
    -0.07
     wife
    -0.07
     wife's
    -0.07
    POSITIVE LOGITS
     autoestima
    0.10
     воспит
    0.10
     bullying
    0.09
     prevenção
    0.09
     тәрби
    0.09
    成长
    0.09
     aprendizagem
    0.09
     negoti
    0.09
     Montessori
    0.09
     adolescents
    0.09
    Act Density 0.034%

    No Known Activations