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

    Neuronpedia

    INDEX
    Explanations

    numbers and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fulfilled
    0.46
     eponymous
    0.45
     sleeveless
    0.44
     surmounted
    0.44
     subsonic
    0.43
     или
    0.43
     atau
    0.42
     dijel
    0.42
     invincible
    0.42
     valued
    0.42
    POSITIVE LOGITS
    aktionen
    0.54
    Medico
    0.48
    intera
    0.47
    people
    0.47
    Preg
    0.46
    ök
    0.46
    Esp
    0.45
    OUR
    0.45
    Some
    0.45
    issues
    0.44
    Act Density 0.136%

    No Known Activations