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

    Neuronpedia

    INDEX
    Explanations

    don

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	sb
    -0.07
     Regents
    -0.06
    ху
    -0.06
     lô
    -0.06
    dd
    -0.06
     nhựa
    -0.06
    ersonic
    -0.06
    726
    -0.06
    para
    -0.06
    ування
    -0.06
    POSITIVE LOGITS
     progresses
    0.07
     gain
    0.07
     ++)
    0.07
    ORDER
    0.07
     потреб
    0.07
    MAC
    0.06
    (il
    0.06
    ागत
    0.06
     lost
    0.06
    _BUFF
    0.06
    Act Density 0.002%

    No Known Activations