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

    Neuronpedia

    INDEX
    Explanations

    positive sentiment and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disadvantage
    0.53
     desvent
    0.47
     ciem
    0.47
    umsuz
    0.46
    Dark
    0.46
     মলিন
    0.44
    DARK
    0.42
    }=-\
    0.42
    싫
    0.42
     kötü
    0.41
    POSITIVE LOGITS
     positive
    1.25
     Positive
    1.13
    Positive
    1.13
     pozitiv
    1.09
     positivo
    1.06
    positive
    1.05
     positivos
    1.05
     positiva
    1.01
     positif
    1.00
     positivas
    1.00
    Act Density 0.563%

    No Known Activations