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

    Neuronpedia

    INDEX
    Explanations

    ancient manuscripts and scrolls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    铁路
    0.79
    acjach
    0.73
     relembrar
    0.72
    公路
    0.70
     पूर्वा
    0.70
    FieldError
    0.70
     lembrar
    0.69
     ferrovi
    0.69
     Fitzsimmons
    0.69
    েনার
    0.69
    POSITIVE LOGITS
     manuscripts
    1.69
     manuscript
    1.66
     Manuscript
    1.59
     Manuscripts
    1.55
     manus
    1.47
    Manus
    1.47
     scroll
    1.46
     पांड
    1.42
     Scroll
    1.40
     scrolls
    1.38
    Act Density 0.020%

    No Known Activations