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

    Neuronpedia

    INDEX
    Explanations

    [[

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    raud
    -0.06
     ="
    -0.06
    ay
    -0.06
     caut
    -0.06
    Generated
    -0.06
    =',
    -0.06
     后
    -0.06
     riv
    -0.06
     Rail
    -0.06
     rail
    -0.06
    POSITIVE LOGITS
     вули
    0.07
     Lead
    0.06
    _secret
    0.06
     abdom
    0.06
    ительства
    0.06
    xFC
    0.06
    对于
    0.06
     kla
    0.06
     Overnight
    0.06
    /T
    0.06
    Act Density 0.002%

    No Known Activations