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

    Neuronpedia

    INDEX
    Explanations

    base

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    תוכ
    -0.07
    clk
    -0.07
     كنت
    -0.07
     squeez
    -0.07
    	cin
    -0.07
    /close
    -0.07
    访问
    -0.07
    setProperty
    -0.07
    Signup
    -0.06
    .ap
    -0.06
    POSITIVE LOGITS
    aji
    0.07
     вообще
    0.07
     realizar
    0.07
     cabo
    0.07
    rosso
    0.07
    狸
    0.07
     não
    0.07
    	Command
    0.07
    .↵↵↵↵↵↵
    0.06
    把自己的
    0.06
    Act Density 0.614%

    No Known Activations