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

    Neuronpedia

    INDEX
    Explanations

    во

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ास
    -0.07
     앉
    -0.07
    CanBe
    -0.07
    receive
    -0.06
     caves
    -0.06
     alice
    -0.06
     usage
    -0.06
    르
    -0.06
     Cous
    -0.06
     Bis
    -0.06
    POSITIVE LOGITS
    utenant
    0.07
    vertime
    0.07
    очного
    0.07
    (directory
    0.07
     Magnum
    0.07
    itime
    0.06
     libert
    0.06
     Hawai
    0.06
     làn
    0.06
     GMO
    0.06
    Act Density 0.003%

    No Known Activations