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

    Neuronpedia

    INDEX
    Explanations

    many [varied groups/things]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )");
    0.91
     настоящий
    0.90
     supremo
    0.89
     daarmee
    0.89
    ]");
    0.85
     cualquier
    0.84
    wijs
    0.84
    (?
    0.82
     preferencia
    0.82
     logra
    0.82
    POSITIVE LOGITS
     sclerosis
    1.37
     universes
    1.08
    s
    1.06
    j
    1.05
    k
    1.02
    د
    1.01
     avenues
    0.99
     kinds
    0.97
    س
    0.97
     dozens
    0.96
    Act Density 0.026%

    No Known Activations