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

    Neuronpedia

    INDEX
    Explanations

    before, after, or bolded items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    um
    0.89
    bibfnamefont
    0.85
    לים
    0.85
    ాన
    0.84
     Zat
    0.83
    un
    0.83
    ל
    0.81
    ala
    0.80
    је
    0.79
    au
    0.78
    POSITIVE LOGITS
     snork
    1.37
     datth
    1.35
     유명
    1.35
    tipo
    1.29
    two
    1.29
     Unión
    1.29
     caliper
    1.26
    ㇁
    1.25
    fromDate
    1.23
     siglos
    1.23
    Act Density 0.002%

    No Known Activations