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

    Neuronpedia

    INDEX
    Explanations

    language models and machine learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    blue
    -0.06
     droit
    -0.06
    ηρε
    -0.06
     Cohen
    -0.06
    CASCADE
    -0.06
    .tests
    -0.06
    	cell
    -0.06
     rval
    -0.05
    APE
    -0.05
     معماری
    -0.05
    POSITIVE LOGITS
    335
    0.06
    �
    0.06
     premi
    0.06
    nox
    0.06
    =""/>↵
    0.06
    .omg
    0.06
    502
    0.06
    	Local
    0.06
    (graph
    0.06
    ========↵
    0.06
    Act Density 0.030%

    No Known Activations