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

    Neuronpedia

    INDEX
    Explanations

    kegs, draft, taps, barrels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.67
     In
    0.66
     Of
    0.58
     IN
    0.56
     For
    0.55
     Washing
    0.54
     th
    0.53
     place
    0.53
     か
    0.53
     AT
    0.53
    POSITIVE LOGITS
    vorschau
    0.61
     таке
    0.54
     fichero
    0.53
    ैक्ट
    0.51
     টেলিগ্রাফ
    0.50
    رس
    0.50
    webElementGuid
    0.50
     аксессу
    0.50
     misrepresented
    0.50
     psicol
    0.49
    Act Density 0.000%

    No Known Activations