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

    Neuronpedia

    INDEX
    Explanations

    psychologytoday.com

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    upstream
    0.69
    ococci
    0.69
    raje
    0.69
     konzerv
    0.68
     തുടങ്ങി
    0.68
     dator
    0.67
     स्नेह
    0.66
     poitrine
    0.66
    regnum
    0.65
    굽
    0.65
    POSITIVE LOGITS
     BeautifulSoup
    0.64
     Cloud
    0.62
     hatched
    0.61
    CommonAncestor
    0.59
     fol
    0.59
     Sensing
    0.59
     Phong
    0.59
     chac
    0.58
     Morning
    0.58
     fan
    0.58
    Act Density 0.046%

    No Known Activations