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

    Neuronpedia

    INDEX
    Explanations

    decline, loss, or passing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iembre
    0.49
    ake
    0.41
    erdapat
    0.41
    étique
    0.40
    合适
    0.39
     dados
    0.39
     शिलालेख
    0.39
    ueda
    0.38
    ịp
    0.38
    强
    0.37
    POSITIVE LOGITS
     enjoyment
    0.47
    Share
    0.46
    CRR
    0.44
    Surely
    0.44
     pleasures
    0.44
     générations
    0.44
     pasión
    0.42
     pleasurable
    0.42
     generations
    0.41
     treasury
    0.41
    Act Density 0.000%

    No Known Activations