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

    Neuronpedia

    INDEX
    Explanations

    or connecting phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Analysts
    0.46
     United
    0.45
     A
    0.43
     emotion
    0.43
     Intelligence
    0.42
     virtu
    0.42
     Collaboration
    0.42
     zdję
    0.42
     targets
    0.41
     Cement
    0.41
    POSITIVE LOGITS
     или
    0.52
     ή
    0.50
     ឬ
    0.49
    거나
    0.45
     அல்லது
    0.45
    ])
    0.44
    หรือ
    0.44
    ('')
    0.44
     或
    0.44
     અથવા
    0.44
    Act Density 0.001%

    No Known Activations