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

    Neuronpedia

    INDEX
    Explanations

    hypotheses, research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    outine
    -0.09
     burnt
    -0.09
     Tutorials
    -0.09
    'écran
    -0.08
     Caring
    -0.08
    zeuge
    -0.08
     În
    -0.08
     jug
    -0.08
     Луч
    -0.08
    nez
    -0.08
    POSITIVE LOGITS
     hypothesis
    0.13
     hypotheses
    0.12
     hypoth
    0.09
     statement
    0.08
     hipot
    0.08
    (Expected
    0.08
    Statement
    0.08
     예상
    0.08
     proposed
    0.08
     Statement
    0.08
    Act Density 0.006%

    No Known Activations