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

    Neuronpedia

    INDEX
    Explanations

    foreign place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     It
    -0.08
     it
    -0.08
    136
    -0.08
    Kate
    -0.07
     marca
    -0.07
     at
    -0.07
    JE
    -0.07
     characterized
    -0.07
    _RECORD
    -0.07
     Kate
    -0.07
    POSITIVE LOGITS
    ный
    0.09
     στον
    0.09
     первый
    0.09
     один
    0.08
    ський
    0.08
     перший
    0.08
     этот
    0.08
     τον
    0.08
    ющий
    0.07
    ний
    0.07
    Act Density 0.097%

    No Known Activations