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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ими
    -0.07
    ctime
    -0.07
    	when
    -0.07
    :.
    -0.07
    Elite
    -0.07
    	op
    -0.07
     числі
    -0.07
     дит
    -0.06
    endsWith
    -0.06
    .ribbon
    -0.06
    POSITIVE LOGITS
    ском
    0.06
     indispens
    0.06
     );↵
    0.06
     Pawn
    0.06
    Layer
    0.06
     acceso
    0.06
     reforms
    0.06
    Anderson
    0.06
    !';↵
    0.06
     ноября
    0.06
    Act Density 0.022%

    No Known Activations