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

    Neuronpedia

    INDEX
    Explanations

    purchase decision phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ましょう
    0.55
     neuronal
    0.54
     ಸಾಮಾನ್ಯವಾಗಿ
    0.54
     episodic
    0.50
     歴史
    0.49
     algebras
    0.48
     culturali
    0.48
     tumult
    0.47
    と考えられる
    0.46
     pathogenesis
    0.46
    POSITIVE LOGITS
     quality
    0.73
     Quality
    0.70
     durability
    0.70
     overpriced
    0.69
     qualità
    0.69
     reviewers
    0.69
     prodotto
    0.68
     reviewer
    0.68
    这款
    0.68
     pricey
    0.68
    Act Density 0.018%

    No Known Activations