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

    Neuronpedia

    INDEX
    Explanations

    ang

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CDF
    -0.07
    ерше
    -0.07
     sábado
    -0.07
     crimson
    -0.07
    状
    -0.07
    ула
    -0.07
     спіль
    -0.07
     siblings
    -0.06
     fatalities
    -0.06
     zač
    -0.06
    POSITIVE LOGITS
     selects
    0.07
    	connection
    0.07
     "!
    0.06
     состоит
    0.06
     {{
    0.06
    .Gr
    0.06
     detained
    0.06
     �
    0.06
    РН
    0.06
    ",$
    0.06
    Act Density 0.005%

    No Known Activations