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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     capacities
    -0.07
    _TAC
    -0.06
    IfNeeded
    -0.06
     OTHER
    -0.06
    MI
    -0.06
    Local
    -0.06
    .getenv
    -0.06
     پرداز
    -0.06
     savvy
    -0.06
     principalTable
    -0.06
    POSITIVE LOGITS
     Oregon
    0.07
    ulkan
    0.07
    =-
    0.07
     asıl
    0.07
     modern
    0.06
    Restore
    0.06
     lớp
    0.06
     пак
    0.06
     économ
    0.06
     भगव
    0.06
    Act Density 0.000%

    No Known Activations