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

    Neuronpedia

    INDEX
    Explanations

    approach this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    아
    0.47
     아이
    0.44
    嵃
    0.43
    iertos
    0.42
    US
    0.42
    에서는
    0.42
     realizaron
    0.41
    精灵
    0.41
     namens
    0.41
    译
    0.41
    POSITIVE LOGITS
     Justice
    0.46
     endanger
    0.46
    justice
    0.44
    Justice
    0.44
     njega
    0.43
     justice
    0.43
    קט
    0.43
     Pandey
    0.43
    ”!
    0.43
     integrity
    0.42
    Act Density 0.009%

    No Known Activations