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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ेज
    -0.08
    eday
    -0.07
    cente
    -0.07
    -radio
    -0.06
     radically
    -0.06
    Project
    -0.06
     июля
    -0.06
     spécial
    -0.06
    hm
    -0.06
    شاه
    -0.06
    POSITIVE LOGITS
    บบ
    0.07
     fres
    0.06
     acct
    0.06
     قسمت
    0.06
     tup
    0.06
     userType
    0.06
     сек
    0.06
    .SerializeObject
    0.06
     Pars
    0.06
     SPEED
    0.06
    Act Density 0.004%

    No Known Activations