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

    Neuronpedia

    INDEX
    Explanations

    after

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NAFTA
    -0.07
     �
    -0.07
     pNode
    -0.07
     Swap
    -0.07
    Chess
    -0.07
     diplomats
    -0.06
    ReturnValue
    -0.06
    .Servlet
    -0.06
     Became
    -0.06
    surname
    -0.06
    POSITIVE LOGITS
     toastr
    0.07
    .Ui
    0.06
    _di
    0.06
    //↵
    0.06
    ViewState
    0.06
    _LOG
    0.06
     تأثیر
    0.06
    )__
    0.06
     lsp
    0.06
    _selector
    0.06
    Act Density 0.000%

    No Known Activations