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

    Neuronpedia

    INDEX
    Explanations

    internship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HttpHeaders
    0.59
    utia
    0.58
    ьте
    0.56
     Miscellaneous
    0.56
    にっいて
    0.56
    Personally
    0.53
    ീ
    0.52
    स्तानी
    0.52
     turmoil
    0.50
     Physic
    0.50
    POSITIVE LOGITS
     davran
    0.66
    ोबर
    0.61
    ла
    0.61
    रिडोर
    0.59
    सिद्ध
    0.58
     партия
    0.58
    ような
    0.58
    `${
    0.56
     Klicken
    0.56
    йс
    0.56
    Act Density 0.008%

    No Known Activations