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

    Neuronpedia

    INDEX
    Explanations

    you can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Collection
    0.48
     Cross
    0.47
     Collegiate
    0.46
    ications
    0.45
     Default
    0.44
    llll
    0.44
    লেক
    0.44
     Computer
    0.44
     لكم
    0.44
     diseg
    0.43
    POSITIVE LOGITS
     ухуд
    0.48
     σήμερα
    0.46
    이란
    0.44
     húmed
    0.43
     présentes
    0.43
    neutrophiles
    0.43
    是对
    0.43
    водит
    0.42
    经历了
    0.42
     arrête
    0.41
    Act Density 0.001%

    No Known Activations