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

    Neuronpedia

    INDEX
    Explanations

    subtly shift conversation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clans
    0.82
    缴纳
    0.79
     alleles
    0.78
     заключения
    0.76
     sonucu
    0.75
     dív
    0.75
    সংঘ
    0.73
    clan
    0.73
    争
    0.73
     Insurance
    0.73
    POSITIVE LOGITS
     curriculum
    1.82
     pedagog
    1.81
     pedagogical
    1.80
     pedagogy
    1.71
     instructional
    1.64
     Curriculum
    1.61
     pédagog
    1.60
     Instructional
    1.58
     curricula
    1.55
     didactic
    1.51
    Act Density 0.504%

    No Known Activations