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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tình
    -0.07
     Tang
    -0.07
    武警
    -0.07
     seks
    -0.07
    济
    -0.07
     birthdays
    -0.06
    cant
    -0.06
    bbe
    -0.06
     בצ
    -0.06
     magn
    -0.06
    POSITIVE LOGITS
    Buffers
    0.07
     ordeal
    0.07
     holster
    0.07
    を使
    0.07
     toys
    0.06
    セット
    0.06
     работе
    0.06
    等原因
    0.06
    同樣
    0.06
    试剂
    0.06
    Act Density 0.003%

    No Known Activations