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

    Neuronpedia

    INDEX
    Explanations

    _schema

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lk
    -0.07
     iz
    -0.07
    .oper
    -0.07
    _ss
    -0.06
     variation
    -0.06
    as
    -0.06
    oltage
    -0.06
    (Box
    -0.06
     bylo
    -0.06
    (net
    -0.06
    POSITIVE LOGITS
     виход
    0.07
    _memory
    0.07
    	mesh
    0.06
    .Safe
    0.06
     выс
    0.06
     Bengals
    0.06
    なお
    0.06
    .management
    0.06
    ░
    0.06
    Photon
    0.06
    Act Density 0.001%

    No Known Activations