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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PhoneNumber
    -0.07
     використовувати
    -0.07
    packageName
    -0.07
     теч
    -0.06
     lowercase
    -0.06
    claimed
    -0.06
    いる
    -0.06
    ESPN
    -0.06
     fauna
    -0.06
     arrangement
    -0.06
    POSITIVE LOGITS
    くらい
    0.07
    >-->↵
    0.07
    	Start
    0.06
    ">-->↵
    0.06
     Gerr
    0.06
     tanı
    0.06
     sah
    0.06
     ]}↵
    0.06
     Persona
    0.06
     accordingly
    0.06
    Act Density 0.052%

    No Known Activations