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

    Neuronpedia

    INDEX
    Explanations

    world

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     그런
    -0.07
    由
    -0.07
    被
    -0.07
    bian
    -0.06
     caret
    -0.06
    SERVICE
    -0.06
    zej
    -0.06
    909
    -0.06
    率
    -0.06
    849
    -0.06
    POSITIVE LOGITS
     periodically
    0.07
     imagin
    0.06
     uncomp
    0.06
    utherford
    0.06
     muht
    0.06
    Ho
    0.06
     множе
    0.06
    ortal
    0.06
    Five
    0.06
     Half
    0.06
    Act Density 0.011%

    No Known Activations