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

    Neuronpedia

    INDEX
    Explanations

    academic acknowledgements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _VLAN
    -0.07
     цен
    -0.07
    acity
    -0.07
    _min
    -0.07
    _MISSING
    -0.07
    вердж
    -0.07
     Ree
    -0.06
     auctions
    -0.06
     utens
    -0.06
    ابق
    -0.06
    POSITIVE LOGITS
    .removeAttribute
    0.07
    Intialized
    0.06
    .available
    0.06
     scraps
    0.06
    ‌انبار
    0.06
    .writ
    0.06
     Trigger
    0.06
     transitional
    0.06
    ENTER
    0.06
    ']?>"
    0.06
    Act Density 0.013%

    No Known Activations