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

    Neuronpedia

    INDEX
    Explanations

    browser developer tools extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bradley
    0.47
    observers
    0.47
    Brady
    0.46
    Mental
    0.45
    Observers
    0.44
    Bruce
    0.44
    Algorithm
    0.44
    SYSTEM
    0.44
    Brother
    0.44
    brother
    0.44
    POSITIVE LOGITS
     instance
    0.46
     sessions
    0.46
     sechs
    0.45
     instances
    0.45
     extensions
    0.45
     pints
    0.43
     solitaire
    0.42
     extension
    0.42
     tabs
    0.42
     fünf
    0.42
    Act Density 0.012%

    No Known Activations