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

    Neuronpedia

    INDEX
    Explanations

    first n, top n

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ete
    0.80
     또한
    0.79
    이란
    0.75
     bởi
    0.73
    ه‌های
    0.73
     คือ
    0.70
    upp
    0.70
    잇
    0.70
    Rite
    0.69
     والذي
    0.69
    POSITIVE LOGITS
     sterilized
    0.82
     immunization
    0.77
     inoculated
    0.76
     sanitized
    0.76
     corral
    0.72
     vaccinated
    0.71
     inoculum
    0.71
     deciduous
    0.71
     lysed
    0.71
     symplectic
    0.70
    Act Density 0.002%

    No Known Activations