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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     하는
    -0.08
    ぬ
    -0.07
    过去
    -0.06
    .any
    -0.06
    かった
    -0.06
    .WriteAll
    -0.06
     있다고
    -0.06
    .badlogic
    -0.06
     Immigration
    -0.06
     sensitivity
    -0.06
    POSITIVE LOGITS
    644
    0.07
    croll
    0.07
    ’te
    0.06
     restraining
    0.06
    ."},↵
    0.06
     Viện
    0.06
    	add
    0.06
    (dialog
    0.06
     leases
    0.06
     Richt
    0.06
    Act Density 0.003%

    No Known Activations