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

    Neuronpedia

    INDEX
    Explanations

    town names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -pop
    -0.07
     NIH
    -0.07
    beta
    -0.07
     organs
    -0.07
     APC
    -0.07
    puts
    -0.07
     majors
    -0.06
    BUF
    -0.06
     motherboard
    -0.06
     perpetrator
    -0.06
    POSITIVE LOGITS
    比例
    0.07
    ‌تواند
    0.06
    _delta
    0.06
    allax
    0.06
     "-"↵
    0.06
    ायन
    0.06
    %↵
    0.06
    ulous
    0.06
    /templates
    0.06
    ={↵
    0.06
    Act Density 0.047%

    No Known Activations