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

    Neuronpedia

    INDEX
    Explanations

    dormitories and dorm rooms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acky
    0.42
     Intern
    0.38
    Intern
    0.38
    oria
    0.36
    achel
    0.36
     osim
    0.36
    igi
    0.36
    úly
    0.36
     som
    0.35
    㙋
    0.35
    POSITIVE LOGITS
     Dorm
    0.54
    itories
    0.53
    dorm
    0.50
     dorm
    0.44
     sfai
    0.43
    ITATION
    0.43
     alfabeto
    0.42
     인생
    0.41
    Ⴌ
    0.40
    ității
    0.40
    Act Density 0.001%

    No Known Activations