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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    武士
    -0.07
    (Msg
    -0.07
     groom
    -0.07
    Point
    -0.07
    -ca
    -0.06
     Лю
    -0.06
     Shard
    -0.06
     Fr
    -0.06
    博士
    -0.06
    绿色
    -0.06
    POSITIVE LOGITS
     гаранти
    0.07
    PostalCodes
    0.07
    ikipedia
    0.07
     ketogenic
    0.06
    LAN
    0.06
    hes
    0.06
    ITICAL
    0.06
    uckland
    0.06
    넋
    0.06
    	seq
    0.06
    Act Density 0.001%

    No Known Activations