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

    Neuronpedia

    INDEX
    Explanations

    NIH

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ghế
    -0.07
    olver
    -0.06
    etr
    -0.06
    ooting
    -0.06
    ulate
    -0.06
    _logger
    -0.06
    lava
    -0.06
    olv
    -0.06
    ání
    -0.06
    	j
    -0.06
    POSITIVE LOGITS
    MING
    0.06
     سرمایه
    0.06
     Melbourne
    0.06
    mir
    0.06
     Mustang
    0.06
    甜
    0.06
     Sud
    0.06
    築
    0.06
    ming
    0.06
     ویژ
    0.06
    Act Density 0.005%

    No Known Activations