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

    Neuronpedia

    INDEX
    Explanations

    analogies and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cumplir
    0.43
     homolog
    0.42
    하자
    0.40
     construye
    0.40
    g
    0.40
     residencial
    0.40
     mangrove
    0.40
     presidencial
    0.40
     extraer
    0.40
     immunized
    0.39
    POSITIVE LOGITS
     iPads
    0.45
     Potatoes
    0.44
     আপ
    0.43
    (
    0.43
     QuickBooks
    0.42
     Beatles
    0.42
    Tunes
    0.42
     মিনিট
    0.42
     बॉबी
    0.42
     গান
    0.41
    Act Density 0.008%

    No Known Activations