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

    Neuronpedia

    INDEX
    Explanations

    mailing list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whale
    0.42
    ibri
    0.40
    lectic
    0.40
    cited
    0.40
     chini
    0.39
     неред
    0.38
     उद्ध
    0.38
    ration
    0.38
    нология
    0.38
     outgrowth
    0.38
    POSITIVE LOGITS
     List
    0.55
    List
    0.52
    list
    0.50
     daftar
    0.48
    గొ
    0.47
     لیست
    0.46
     list
    0.46
     Address
    0.46
    Список
    0.46
    LIST
    0.46
    Act Density 0.001%

    No Known Activations