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

    Neuronpedia

    INDEX
    Explanations

    lists, instructions, ratings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дозвол
    -0.09
     regret
    -0.08
     ذهب
    -0.08
    _Reg
    -0.07
     préd
    -0.07
     наша
    -0.07
     для
    -0.07
     regrets
    -0.07
     잠
    -0.07
     grounded
    -0.07
    POSITIVE LOGITS
     Bangalore
    0.08
     verschijnt
    0.08
    DU
    0.07
     devas
    0.07
    Recommend
    0.07
     respons
    0.07
    aho
    0.07
     biome
    0.07
     आरोप
    0.07
    itag
    0.07
    Act Density 0.000%

    No Known Activations