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

    Neuronpedia

    INDEX
    Explanations

    rate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CS
    -0.07
     Palo
    -0.07
    díl
    -0.07
    语
    -0.07
     Gospel
    -0.07
     Soul
    -0.06
     grew
    -0.06
     directs
    -0.06
     schö
    -0.06
    SHOW
    -0.06
    POSITIVE LOGITS
    minate
    0.07
    .Receive
    0.07
     Cases
    0.06
    واع
    0.06
    ै.↵
    0.06
     uplat
    0.06
    :Set
    0.06
    ETweet
    0.06
    .depend
    0.06
    CLOSE
    0.06
    Act Density 0.011%

    No Known Activations