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

    Neuronpedia

    INDEX
    Explanations

    entity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =np
    -0.06
    ,K
    -0.06
     जनत
    -0.06
     depths
    -0.06
    (np
    -0.06
    -active
    -0.06
    ickle
    -0.06
    Cs
    -0.06
    िद
    -0.06
     deutschen
    -0.06
    POSITIVE LOGITS
    Library
    0.07
     ballpark
    0.07
     لیگ
    0.07
    application
    0.07
     vacations
    0.07
    处理
    0.06
     libraries
    0.06
    atest
    0.06
    Specification
    0.06
     біблі
    0.06
    Act Density 0.043%

    No Known Activations