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

    Neuronpedia

    INDEX
    Explanations

    locations around the world

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    terior
    -0.07
     IoT
    -0.07
     Tro
    -0.06
    CORE
    -0.06
     Foster
    -0.06
     Theater
    -0.06
    _flip
    -0.06
     Qatar
    -0.06
     Distrib
    -0.06
     Couch
    -0.06
    POSITIVE LOGITS
    增
    0.06
    sizlik
    0.06
    ві
    0.06
     soaked
    0.06
     {:?}",
    0.06
    (klass
    0.06
    insi
    0.06
    ург
    0.06
     """",↵
    0.06
    yasal
    0.06
    Act Density 0.020%

    No Known Activations