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

    Neuronpedia

    INDEX
    Explanations

    Code and web references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    过去
    -0.07
     consulta
    -0.06
     heap
    -0.06
    	pid
    -0.06
     Пари
    -0.06
     kterou
    -0.06
    ци
    -0.06
    세
    -0.06
     샤
    -0.06
    Keeping
    -0.06
    POSITIVE LOGITS
    _standard
    0.06
    \xff
    0.06
    麼
    0.06
    cheduling
    0.06
    missive
    0.06
    (defun
    0.06
    輔
    0.06
     buffered
    0.06
    腐
    0.06
     NON
    0.06
    Act Density 0.027%

    No Known Activations