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

    Neuronpedia

    INDEX
    Explanations

    finding a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мобиль
    0.46
    bringing
    0.45
    AMS
    0.44
    nashvillehousing
    0.44
     breed
    0.44
     literacy
    0.43
     covalent
    0.43
     pyro
    0.43
    भीर
    0.42
    Muh
    0.42
    POSITIVE LOGITS
     eventi
    0.42
    ">,</
    0.41
    冲突
    0.41
     avanz
    0.40
    IllegalArgument
    0.40
     Exception
    0.39
    étation
    0.39
     Randolph
    0.39
    bigskip
    0.39
     izgled
    0.38
    Act Density 0.010%

    No Known Activations