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

    Neuronpedia

    INDEX
    Explanations

    others

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     City
    -0.07
    cean
    -0.07
    -wheel
    -0.06
    ump
    -0.06
    ISO
    -0.06
     distribution
    -0.06
    Hung
    -0.06
    castle
    -0.06
     train
    -0.06
     wholesome
    -0.06
    POSITIVE LOGITS
     служ
    0.07
    others
    0.07
    **(
    0.07
     alot
    0.07
    l
    0.07
     TAS
    0.07
     sogar
    0.07
    	Context
    0.07
     {});↵↵
    0.07
     others
    0.06
    Act Density 0.019%

    No Known Activations