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

    Neuronpedia

    INDEX
    Explanations

    ling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     відповід
    -0.06
     Woche
    -0.06
    \.
    -0.06
    args
    -0.06
    ρευ
    -0.06
     RCA
    -0.06
     konz
    -0.06
     chiếu
    -0.06
    ’,
    -0.06
     europ
    -0.06
    POSITIVE LOGITS
    ingle
    0.13
    ingles
    0.11
     mingle
    0.09
    INGLE
    0.08
    ling
    0.08
    _disabled
    0.07
    uestos
    0.07
    ittle
    0.07
    _table
    0.07
    erequisites
    0.06
    Act Density 0.002%

    No Known Activations