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

    Neuronpedia

    INDEX
    Explanations

    technical/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contradictory
    -0.07
     claws
    -0.06
     constitutes
    -0.06
     khá
    -0.06
     væ
    -0.06
    _SHIFT
    -0.06
     شیر
    -0.06
     starší
    -0.06
     deposits
    -0.06
     produce
    -0.06
    POSITIVE LOGITS
     Memorial
    0.06
    idata
    0.06
     connector
    0.06
     conseguir
    0.06
    (byte
    0.06
     данные
    0.06
    lif
    0.06
    _common
    0.06
     Result
    0.06
     One
    0.06
    Act Density 0.001%

    No Known Activations