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

    Neuronpedia

    INDEX
    Explanations

    passports and official documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.54
     heter
    0.46
     January
    0.46
     asymmetry
    0.46
     Coulomb
    0.45
     heterogeneity
    0.44
     poverty
    0.43
    "
    0.43
    v
    0.42
     sanitation
    0.41
    POSITIVE LOGITS
     NVIC
    0.56
     বৈঠক
    0.54
     Lombok
    0.52
    블릿
    0.51
    ❏
    0.51
    0.50
    槃
    0.49
    鹿児島
    0.49
     비슷
    0.49
     vacanam
    0.48
    Act Density 0.003%

    No Known Activations