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

    Neuronpedia

    INDEX
    Explanations

    cache

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -----↵↵
    -0.07
    heatmap
    -0.07
    (atom
    -0.07
    (MigrationBuilder
    -0.06
     self
    -0.06
     CONNECT
    -0.06
     oppos
    -0.06
    .....↵↵
    -0.06
     прест
    -0.06
     ostream
    -0.06
    POSITIVE LOGITS
     Vy
    0.08
     bub
    0.07
     upside
    0.07
     politic
    0.07
     représ
    0.06
     Carnival
    0.06
    216
    0.06
    (PyObject
    0.06
     alloys
    0.06
     Arab
    0.06
    Act Density 0.005%

    No Known Activations