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

    Neuronpedia

    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    proof
    -0.06
    .sid
    -0.06
    utin
    -0.06
    у
    -0.06
     Laurent
    -0.06
    .rf
    -0.06
     svenska
    -0.06
    .sul
    -0.06
     crude
    -0.06
     Dahl
    -0.06
    POSITIVE LOGITS
    ),
    0.07
     jumped
    0.07
    抬
    0.07
     evaluations
    0.07
    iere
    0.07
    0.06
     감
    0.06
    )];
    0.06
     userdata
    0.06
    jdbc
    0.06
    Act Density 0.000%

    No Known Activations