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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     požadav
    -0.06
    .Sum
    -0.06
     pym
    -0.06
    цен
    -0.06
     Rud
    -0.06
    imeline
    -0.06
     заклад
    -0.06
    Volumes
    -0.06
     Ca
    -0.06
     císa
    -0.06
    POSITIVE LOGITS
     or
    0.09
    ER
    0.08
    artner
    0.08
     제
    0.07
    	first
    0.07
    ster
    0.07
    atter
    0.07
    OFF
    0.07
    _hom
    0.07
    isode
    0.07
    Act Density 0.029%

    No Known Activations