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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xử
    -0.07
     Motion
    -0.06
    
    -0.06
     mingle
    -0.06
    大的
    -0.06
    ym
    -0.06
    another
    -0.06
     bruises
    -0.06
    Problem
    -0.06
    bounce
    -0.06
    POSITIVE LOGITS
    ա
    0.07
     Sind
    0.07
     afterwards
    0.06
     Xavier
    0.06
    _ORD
    0.06
    .inspect
    0.06
     Miner
    0.06
     COPYRIGHT
    0.06
    .rgb
    0.06
     Recording
    0.06
    Act Density 0.000%

    No Known Activations