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

    Neuronpedia

    INDEX
    Explanations

    Knight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    든
    -0.07
     уров
    -0.06
     island
    -0.06
     dio
    -0.06
     له
    -0.06
    .constraints
    -0.06
    들에게
    -0.06
    дами
    -0.06
    DEN
    -0.06
    δας
    -0.06
    POSITIVE LOGITS
     faithfully
    0.07
     namedtuple
    0.07
    ibling
    0.06
     may
    0.06
     newList
    0.06
    kill
    0.06
     cloning
    0.06
     sklad
    0.06
    Draft
    0.06
    decrypt
    0.06
    Act Density 0.000%

    No Known Activations