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

    Neuronpedia

    INDEX
    Explanations

    -like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /tree
    -0.08
     current
    -0.07
    =d
    -0.07
     워
    -0.07
    btc
    -0.06
    �
    -0.06
    청
    -0.06
    .DataBindings
    -0.06
     diarr
    -0.06
    zburg
    -0.06
    POSITIVE LOGITS
     Helps
    0.07
    {
↵
↵
    0.07
    IFORM
    0.06
     RemoteException
    0.06
    оля
    0.06
    agment
    0.06
     dispos
    0.06
     charm
    0.06
     PROGRAM
    0.06
     driveway
    0.06
    Act Density 0.003%

    No Known Activations