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

    Neuronpedia

    INDEX
    Explanations

    output =

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Thirteen
    0.39
    十三
    0.37
    hanam
    0.37
    函数
    0.36
    юз
    0.36
    HttpPost
    0.36
     бк
    0.36
    Ethoxy
    0.35
    Fprintf
    0.35
    整数
    0.35
    POSITIVE LOGITS
     App
    0.34
     ори
    0.34
     occurred
    0.34
    igenschaft
    0.34
    צר
    0.33
    羣
    0.33
     SLAs
    0.32
     occur
    0.32
     paths
    0.32
     قرار
    0.32
    Act Density 0.001%

    No Known Activations