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

    Neuronpedia

    INDEX
    Explanations

    childhood activities and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دانشج
    0.62
     деву
    0.50
     mahasiswa
    0.48
     étudiants
    0.47
     सेक्सी
    0.45
    젠
    0.44
     alphan
    0.44
     parturient
    0.44
    🍾
    0.43
     студентов
    0.43
    POSITIVE LOGITS
     todd
    0.79
    👧
    0.78
    🧒
    0.74
     tantrums
    0.73
     Lego
    0.73
     crayons
    0.72
     crayon
    0.71
     Mommy
    0.71
     gig
    0.70
     playground
    0.70
    Act Density 0.119%

    No Known Activations