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

    Neuronpedia

    INDEX
    Explanations

    balls and boxes questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uf
    -0.07
     altru
    -0.07
     Firmware
    -0.07
    oeff
    -0.06
     saf
    -0.06
    ражд
    -0.06
     Creating
    -0.06
     ary
    -0.06
    dens
    -0.06
    	cc
    -0.06
    POSITIVE LOGITS
     рекомендуется
    0.07
     要
    0.07
     vyžad
    0.06
     منابع
    0.06
     рід
    0.06
    _SEND
    0.06
    ζη
    0.06
     v�
    0.06
    <Select
    0.06
     一般
    0.06
    Act Density 0.010%

    No Known Activations