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

    Neuronpedia

    INDEX
    Explanations

    automatic transmission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পর্যবে
    0.61
     artesan
    0.59
     seguridad
    0.56
     activación
    0.56
     situação
    0.55
    룀
    0.55
     filtros
    0.55
    Щ
    0.55
     fotograf
    0.54
    ﺡ
    0.54
    POSITIVE LOGITS
     was
    0.61
     also
    0.60
     \
    0.58
     teaching
    0.57
     metastatic
    0.57
    er
    0.56
    ce
    0.55
    veled
    0.55
    出来的
    0.55
     daughter
    0.54
    Act Density 0.000%

    No Known Activations